Raincloud/2025-02-BondingArtifact
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
9b63f2fff32ffa3b3390f7c6c6332f5bf1967948
2025-02-BondingArtifact/.specstory/history/2025-10-29_05-09Z-denoising-image-sequence-in-blender.md
Raincloud 9b63f2fff3 sorted denoising cheat
2025-10-30 01:03:40 -06:00

2696 lines
78 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<!-- Generated by SpecStory -->
<!-- cursor Session 80c63c63-a657-4ae3-a4d1-611dca0cc8cd (2025-10-29 05:09Z) -->
# Denoising image sequence in Blender (2025-10-29 05:09Z)
_**User (2025-10-29 05:09Z)**_
I have a rendered image sequence. How can I denoise it in blender 4.5?
---
_**Assistant (default)**_
---
Checking Blender 4.5 denoising options for rendered image sequences.
---
Tool use: **web_search**
<details>
<summary>Searched web `Blender 4.5 denoise image sequence render` • **1** results</summary>
| Title | URL | Chunk |
|-------|-----|-------|
| Web Search Results | | To denoise a rendered image sequence in Blender 4.5, you can utilize the Denoise node within the Compositor. Here's a step-by-step guide:<br/><br/>1. **Open a New Blender Project**: Launch Blender and create a new project.<br/><br/>2. **Access the Compositor**: Navigate to the **Compositing** workspace by clicking on the **Compositing** tab at the top of the Blender interface.<br/><br/>3. **Enable Nodes**: In the Compositor, check the **Use Nodes** box to activate node-based compositing.<br/><br/>4. **Remove Default Nodes**: By default, Blender adds a **Render Layers** node. Since you're working with an existing image sequence, delete this node by selecting it and pressing **X**.<br/><br/>5. **Add an Image Sequence Node**:<br/> - Press **Shift + A** to open the Add menu.<br/> - Navigate to **Input** > **Image** to add an Image node.<br/> - In the Image node properties, click **Open** and select the first image of your sequence.<br/> - Enable the **Sequence** checkbox.<br/> - Set the **Frames** value to the total number of images in your sequence.<br/> - Adjust the **Start Frame** if your sequence doesn't begin at frame 1.<br/><br/>6. **Add a Denoise Node**:<br/> - Press **Shift + A** and go to **Filter** > **Denoise** to add a Denoise node.<br/> - Connect the **Image** output of the Image node to the **Image** input of the Denoise node.<br/><br/>7. **Connect to Composite Output**:<br/> - Ensure there's a **Composite** node in your setup. If not, add one by pressing **Shift + A** and selecting **Output** > **Composite**.<br/> - Connect the **Image** output of the Denoise node to the **Image** input of the Composite node.<br/><br/>8. **Set Output Properties**:<br/> - In the **Output Properties** panel (printer icon), specify the output folder and file format for the denoised sequence.<br/> - Ensure the **Frame Start** and **End** match your image sequence.<br/><br/>9. **Render the Denoised Sequence**:<br/> - Go to the **Render** menu and select **Render Animation**.<br/> - Blender will process each frame through the Compositor, applying the denoising effect, and save the denoised images to your specified output folder.<br/><br/>This method allows you to denoise an existing image sequence without re-rendering the original scene. However, it's important to note that denoising in post-processing may not achieve the same quality as denoising during the initial render, especially if the original render lacks necessary passes like Denoising Normal and Denoising Albedo. For optimal results, consider enabling denoising data passes during rendering. ([docs.blender.org](https://docs.blender.org/manual/en/latest/compositing/types/filter/denoise.html?utm_source=openai))<br/><br/>Additionally, Blender 4.5 introduces GPU support for the Open Image Denoise-based Denoise node, potentially improving performance during the denoising process. ([cgchannel.com](https://www.cgchannel.com/2025/07/blender-4-5-lts-is-out-check-out-its-5-key-features/?utm_source=openai)) |
</details>
---
---
How to denoise an image sequence in Blender 4.5:
- Set the Output Properties:
1. Output Properties (printer) → choose a folder and format (PNG/EXR).
2. Set Frame Start/End to match your sequence range.
- In Compositor:
1. Enable Use Nodes and remove the default Render Layers node.
2. Add Input > Image:
- Open the first frame.
- Enable Sequence.
- Set Frames to the total count.
- Adjust Start Frame if not frame 1.
3. Add Filter > Denoise: image → denoise.
4. Connect denoise image → Composite input.
- For better results (if available):
- If the sequence includes passes, feed Albedo and Normal to the Denoise node.
- If not, use Denoise with image only; quality may be lower.
- Render: Render > Render Animation. Blender will render the frames with denoising applied.
Note: The Denoise node supports GPU in Blender 4.5 for faster processing.
---
Tool use: **mcp_blender_get_viewport_screenshot**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - get_viewport_screenshot:
Capture a screenshot of the current Blender 3D viewport.
Parameters:
- max_size: Maximum size in pixels for the largest dimension (default: 800)
Returns the screenshot as an Image.
*Parameters*:
* max_size: 800
*Result*:
Error executing tool get_viewport_screenshot: Screenshot failed: Could not connect to Blender. Make sure the Blender addon is running.
</details>
---
---
## Quick setup
1. Workspace: Compositing
2. Enable Use Nodes
3. Add Input > Image (load first frame; check Sequence)
4. Add Filter > Denoise
5. Connect: Image → Denoise → Composite
6. Set output folder in Output Properties
7. Render Animation
OpenImageDenoise-based GPU denoising is available in Blender 4.5.
If you need help setting it up or want the exact node setup, say which sequence to process.
---
_**User (2025-10-29 05:09Z)**_
check my node setup. the denoising seems really low quality.
---
_**Assistant (default)**_
---
Tool use: **mcp_blender_get_scene_info**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - get_scene_info: Get detailed information about the current Blender scene
*Parameters*:
*
*Result*:
{
"name": "BondingArtifact",
"object_count": 3,
"objects": [
{
"name": "BondingArtifact_Scene",
"type": "EMPTY",
"location": [
0.0,
0.0,
0.0
]
},
{
"name": "Camera",
"type": "CAMERA",
"location": [
-50.42,
38.27,
31.34
]
},
{
"name": "persp",
"type": "CAMERA",
"location": [
-56.43,
38.55,
31.42
]
}
],
"materials_count": 34
}
</details>
---
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: import bpy
# Get the compositor
scene = bpy.context.scene
tree = scene.node_tree
if tree is None:
print("No compositor node tree found")
else:
print("Compositor Nodes:")
print(f"Type: {tree.type}")
for node in tree.nodes:
print(f"\n--- {node.name} ({node.bl_idname}) ---")
print(f"Location: {node.location}")
if hasattr(node, 'inputs'):
print(f"Inputs: {len(node.inputs)}")
for inp in node.inputs:
print(f" - {inp.name} ({inp.type})")
if hasattr(node, 'outputs'):
print(f"Outputs: {len(node.outputs)}")
for out in node.outputs:
print(f" - {out.name} ({out.type})")
# Check for specific properties
if hasattr(node, 'image'):
if node.image:
print(f"Image: {node.image.name}")
if hasattr(node, 'use_sequence'):
print(f"Use Sequence: {node.use_sequence}")
if hasattr(node, 'frame_start'):
print(f"Frame Start: {node.frame_start}")
if hasattr(node, 'frame_duration'):
print(f"Frame Duration: {node.frame_duration}")
if hasattr(node, 'denoise_prefilter'):
print(f"Denoise Prefilter: {node.denoise_prefilter}")
if hasattr(node, 'denoise_strength'):
print(f"Denoise Strength: {node.denoise_strength}")
*Result*:
Code executed successfully: Compositor Nodes:
Type: COMPOSITING
--- Composite (CompositorNodeComposite) ---
Location: <Vector (200.0000, 0.0000)>
Inputs: 1
- Image (RGBA)
Outputs: 0
--- Render Layers (CompositorNodeRLayers) ---
Location: <Vector (-504.2065, 129.0187)>
Inputs: 0
Outputs: 31
- Image (RGBA)
- Alpha (VALUE)
- Depth (VALUE)
- Noisy Image (RGBA)
- Normal (VECTOR)
- UV (VECTOR)
- Vector (VECTOR)
- Position (VECTOR)
- Deprecated (RGBA)
- Deprecated (RGBA)
- Shadow (RGBA)
- AO (RGBA)
- Deprecated (RGBA)
- Deprecated (RGBA)
- Deprecated (RGBA)
- IndexOB (VALUE)
- IndexMA (VALUE)
- Mist (VALUE)
- Emit (RGBA)
- Env (RGBA)
- DiffDir (RGBA)
- DiffInd (RGBA)
- DiffCol (RGBA)
- GlossDir (RGBA)
- GlossInd (RGBA)
- GlossCol (RGBA)
- TransDir (RGBA)
- TransInd (RGBA)
- TransCol (RGBA)
- SubsurfaceDir (RGBA)
- SubsurfaceInd (RGBA)
--- Reroute (NodeReroute) ---
Location: <Vector (100.0000, -35.0000)>
Inputs: 1
- Input (RGBA)
Outputs: 1
- Output (RGBA)
--- Viewer (CompositorNodeViewer) ---
Location: <Vector (200.0000, -60.0000)>
Inputs: 1
- Image (RGBA)
Outputs: 0
--- Denoise (CompositorNodeDenoise) ---
Location: <Vector (-85.0000, 5.5118)>
Inputs: 4
- Image (RGBA)
- Normal (VECTOR)
- Albedo (RGBA)
- HDR (BOOLEAN)
Outputs: 1
- Image (RGBA)
--- Image (CompositorNodeImage) ---
Location: <Vector (-492.0496, -269.2339)>
Inputs: 0
Outputs: 2
- Image (RGBA)
- Alpha (VALUE)
Image: 3_background_dark_0000.png
Frame Start: 0
Frame Duration: 14401
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check the actual connections
scene = bpy.context.scene
tree = scene.node_tree
print("CONNECTIONS:")
for link in tree.links:
print(f"{link.from_node.name}.{link.from_socket.name} -> {link.to_node.name}.{link.to_socket.name}")
# Get specific info about the Denoise node
denoise = tree.nodes.get("Denoise")
if denoise:
print("\n=== DENOISE NODE SETTINGS ===")
for inp in denoise.inputs:
print(f"{inp.name}:")
print(f" - Type: {inp.type}")
print(f" - Enabled: {inp.enabled}")
if inp.is_linked:
print(f" - Linked to: {inp.links[0].from_socket.name} from {inp.links[0].from_node.name}")
if hasattr(inp, 'default_value') and inp.type != 'RGBA':
if hasattr(inp.default_value, '__len__'):
print(f" - Default: {inp.default_value}")
else:
print(f" - Default: {inp.default_value}")
print(f"\nHDR setting: {denoise.hdr}")
print(f"Prefilter: {denoise.prefilter}")
*Result*:
Error executing code: Communication error with Blender: Code execution error: 'CompositorNodeDenoise' object has no attribute 'hdr'
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check the actual connections
scene = bpy.context.scene
tree = scene.node_tree
print("CONNECTIONS:")
for link in tree.links:
print(f"{link.from_node.name}.{link.from_socket.name} -> {link.to_node.name}.{link.to_socket.name}")
# Get specific info about the Denoise node
denoise = tree.nodes.get("Denoise")
if denoise:
print("\n=== DENOISE NODE SETTINGS ===")
# Print all denoise node properties
print("\nAll Denoise node attributes:")
for attr in dir(denoise):
if not attr.startswith('_') and not callable(getattr(denoise, attr)):
try:
value = getattr(denoise, attr)
print(f" {attr}: {value}")
except:
pass
*Result*:
Code executed successfully: CONNECTIONS:
Denoise.Image -> Reroute.Input
Reroute.Output -> Composite.Image
Reroute.Output -> Viewer.Image
Image.Image -> Denoise.Image
=== DENOISE NODE SETTINGS ===
All Denoise node attributes:
bl_description: Denoise renders from Cycles and other ray tracing renderers
bl_height_default: 100.0
bl_height_max: 30.0
bl_height_min: 30.0
bl_icon: NONE
bl_idname: CompositorNodeDenoise
bl_label: Denoise
bl_rna: <bpy_struct, Struct("CompositorNodeDenoise") at 0x00007FF62083F420>
bl_static_type: DENOISE
bl_width_default: 140.0
bl_width_max: 700.0
bl_width_min: 100.0
color: <Color (r=0.6080, g=0.6080, b=0.6080)>
color_tag: FILTER
dimensions: <Vector (140.0000, 240.0000)>
height: 100.0
hide: False
inputs: <bpy_collection[4], NodeInputs>
internal_links: <bpy_collection[1], CompositorNodeDenoise.internal_links>
label:
location: <Vector (-85.0000, 5.5118)>
location_absolute: <Vector (-85.0000, 5.5118)>
mute: False
name: Denoise
outputs: <bpy_collection[1], NodeOutputs>
parent: None
prefilter: ACCURATE
quality: HIGH
rna_type: <bpy_struct, Struct("CompositorNodeDenoise") at 0x00007FF62083F420>
select: False
show_options: True
show_preview: False
show_texture: False
type: DENOISE
use_custom_color: False
use_hdr: True
warning_propagation: ALL
width: 140.0
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check each input to the Denoise node
denoise = bpy.context.scene.node_tree.nodes.get("Denoise")
print("=== DENOISE INPUT STATUS ===")
for inp in denoise.inputs:
print(f"\n{inp.name}:")
print(f" Enabled: {inp.enabled}")
print(f" Is Linked: {inp.is_linked}")
if inp.is_linked:
link = inp.links[0]
print(f" Connected from: {link.from_node.name}.{link.from_socket.name}")
else:
print(f" NOT CONNECTED - This is likely causing low quality denoising!")
*Result*:
Code executed successfully: === DENOISE INPUT STATUS ===
Image:
Enabled: True
Is Linked: True
Connected from: Image.Image
Normal:
Enabled: True
Is Linked: False
NOT CONNECTED - This is likely causing low quality denoising!
Albedo:
Enabled: True
Is Linked: False
NOT CONNECTED - This is likely causing low quality denoising!
HDR:
Enabled: True
Is Linked: False
NOT CONNECTED - This is likely causing low quality denoising!
</details>
---
---
Only the Image input is connected; Normal and Albedo are missing, causing lower-quality denoising. Checking what image format you're using:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check the Image node
img_node = bpy.context.scene.node_tree.nodes.get("Image")
if img_node and img_node.image:
img = img_node.image
print(f"=== IMAGE DETAILS ===")
print(f"Name: {img.name}")
print(f"Size: {img.size[0]}x{img.size[1]}")
print(f"Format: {'HDR' if img.use_float else 'LDR'}")
print(f"Color Space: {img.colorspace_settings.name}")
print(f"File Path: {img.filepath}")
print(f"Use Sequence: {img_node.use_sequence}")
print(f"Frame Start: {img_node.frame_start}")
print(f"Frame Duration: {img_node.frame_duration}")
*Result*:
Error executing code: Communication error with Blender: Code execution error: 'Image' object has no attribute 'use_float'
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check the Image node
img_node = bpy.context.scene.node_tree.nodes.get("Image")
if img_node and img_node.image:
img = img_node.image
print(f"=== IMAGE DETAILS ===")
print(f"Name: {img.name}")
print(f"Size: {img.size[0]}x{img.size[1]}")
print(f"File Path: {img.filepath}")
print(f"Alpha Channel: {img.alpha_mode}")
print(f"\nImage Node:")
print(f"Use Sequence: {img_node.use_sequence}")
print(f"Frame Start: {img_node.frame_start}")
print(f"Frame Duration: {img_node.frame_duration}")
*Result*:
Error executing code: Communication error with Blender: Code execution error: 'CompositorNodeImage' object has no attribute 'use_sequence'
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check the Image node properties
img_node = bpy.context.scene.node_tree.nodes.get("Image")
print(f"=== IMAGE NODE ===")
if img_node and img_node.image:
img = img_node.image
print(f"Name: {img.name}")
print(f"Size: {img.size[0]}x{img.size[1]}")
# Print all image node properties that might be relevant
for attr in ['frame_start', 'frame_duration', 'frame_offset', 'use_alpha']:
if hasattr(img_node, attr):
print(f"{attr}: {getattr(img_node, attr)}")
*Result*:
Code executed successfully: === IMAGE NODE ===
Name: 3_background_dark_0000.png
Size: 3840x2160
frame_start: 0
frame_duration: 14401
frame_offset: 0
</details>
---
---
Denoising an image sequence (PNGs) with only the Image connected; Normal and Albedo are missing, leading to lower quality. For best results, those passes are needed.
Options:
- If you have the source render with passes, plug Normal and Albedo into Denoise; HDR should match the source.
- If not, post-process denoising will be limited.
Checking image format and options with the current setup:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check if the image is HDR or LDR
img_node = bpy.context.scene.node_tree.nodes.get("Image")
img = img_node.image
print(f"Image: {img.name}")
print(f"Is .exr or .hdr: {img.name.lower().endswith(('.exr', '.hdr'))}")
# Check available denoise settings
denoise = bpy.context.scene.node_tree.nodes.get("Denoise")
print(f"\nDenoise settings:")
print(f"Prefilter: {denoise.prefilter}")
print(f"Quality: {denoise.quality}")
print(f"Use HDR: {denoise.use_hdr}")
*Result*:
Code executed successfully: Image: 3_background_dark_0000.png
Is .exr or .hdr: False
Denoise settings:
Prefilter: ACCURATE
Quality: HIGH
Use HDR: True
</details>
---
---
Denoise is set to HDR, but the sequence is PNG (LDR). This mismatch degrades quality. Disabling HDR to match the images.
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Fix the Denoise node for LDR images
denoise = bpy.context.scene.node_tree.nodes.get("Denoise")
denoise.use_hdr = False
# Also check if we should change prefilter
# For standalone images without passes, FAST might work better
denoise.prefilter = 'FAST'
print("=== UPDATED DENOISE SETTINGS ===")
print(f"Use HDR: {denoise.use_hdr} (should be False for PNG)")
print(f"Prefilter: {denoise.prefilter}")
print(f"Quality: {denoise.quality}")
*Result*:
Code executed successfully: === UPDATED DENOISE SETTINGS ===
Use HDR: False (should be False for PNG)
Prefilter: FAST
Quality: HIGH
</details>
---
---
Fixed. The Denoise node was set to HDR while the inputs are PNGs (LDR). Changes:
- Set HDR to Off for LDR images
- Prefilter set to FAST
---
Tool use: **mcp_blender_get_viewport_screenshot**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - get_viewport_screenshot:
Capture a screenshot of the current Blender 3D viewport.
Parameters:
- max_size: Maximum size in pixels for the largest dimension (default: 800)
Returns the screenshot as an Image.
*Parameters*:
* max_size: 800
*Result*:
Error executing tool get_viewport_screenshot: Screenshot failed: No 3D viewport found
</details>
---
---
For better denoising quality:
1. Denoise node settings:
- Enable HDR only if using EXR/HDR
- Set Prefilter to FAST without denoising passes
- Prefilter ACCURATE requires Normal/Albedo passes
2. If you have the original blend: re-render with passes
- Render Properties → Passes → enable Denoising Data → Denoising Normal → Denoising Albedo
3. Alternative: Filter > Kuwahara (artistic smoothing) for post-process only
Render the compositor output to verify the result.
---
_**User (2025-10-29 05:09Z)**_
the resultant mp4 has no denoising.
---
_**Assistant (default)**_
---
Checking why denoising isn't being applied to the output.
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check all connections and verify the compositor is set to use nodes
scene = bpy.context.scene
tree = scene.node_tree
print("=== COMPOSITOR STATE ===")
print(f"Use Nodes: {tree.use_nodes}")
print(f"\nAll Nodes:")
for node in tree.nodes:
print(f" - {node.name} ({node.bl_idname})")
print(f"\n=== ALL CONNECTIONS ===")
for link in tree.links:
print(f"{link.from_node.name}.{link.from_socket.name} -> {link.to_node.name}.{link.to_socket.name}")
# Check if Render Layers is still active
render_layers = tree.nodes.get("Render Layers")
if render_layers:
print(f"\nRender Layers node exists - this might be interfering!")
*Result*:
Error executing code: Communication error with Blender: Code execution error: 'CompositorNodeTree' object has no attribute 'use_nodes'
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check the compositor setup
scene = bpy.context.scene
tree = scene.node_tree
# Check for compositor activation in scene properties
print("=== COMPOSITOR & RENDER SETTINGS ===")
print(f"Compositor enabled: {scene.use_nodes}")
print(f"Compositor type: {tree.type}")
# Check all connections
print(f"\n=== CONNECTIONS ===")
for link in tree.links:
print(f"{link.from_node.name}.{link.from_socket.name} -> {link.to_node.name}.{link.to_socket.name}")
# Check if there's a connection bypassing the Denoise node
print(f"\n=== ROUTING CHECK ===")
composite = tree.nodes.get("Composite")
viewer = tree.nodes.get("Viewer")
reroute = tree.nodes.get("Reroute")
if composite and composite.inputs['Image'].is_linked:
link_to_comp = composite.inputs['Image'].links[0]
print(f"Composite Image input connected from: {link_to_comp.from_node.name}")
if reroute:
print(f"Reroute location: {reroute.location}")
for inp in reroute.inputs:
if inp.is_linked:
print(f" Input connected from: {inp.links[0].from_node.name}")
*Result*:
Code executed successfully: === COMPOSITOR & RENDER SETTINGS ===
Compositor enabled: True
Compositor type: COMPOSITING
=== CONNECTIONS ===
Denoise.Image -> Reroute.Input
Reroute.Output -> Composite.Image
Reroute.Output -> Viewer.Image
Image.Image -> Denoise.Image
=== ROUTING CHECK ===
Composite Image input connected from: Reroute
Reroute location: <Vector (100.0000, -35.0000)>
Input connected from: Denoise
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check render settings
scene = bpy.context.scene
print("=== RENDER SETTINGS ===")
print(f"Engine: {scene.render.engine}")
print(f"Output file format: {scene.render.image_settings.file_format}")
print(f"Codec: {scene.render.ffmpeg.format}")
print(f"Codec video: {scene.render.ffmpeg.codec}")
# Check output path
print(f"\nOutput path: {scene.render.filepath}")
# Check if compositor is being bypassed
print(f"\n=== COMPOSITOR SETTINGS ===")
print(f"Compositor enabled in scene: {scene.use_compositor}")
print(f"Compositor mode: {scene.use_compositor}")
# Check if using nodes
tree = scene.node_tree
print(f"Active compositor nodes tree exists: {tree is not None}")
*Result*:
Error executing code: Communication error with Blender: Code execution error: 'Scene' object has no attribute 'use_compositor'
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check render and output settings
scene = bpy.context.scene
print("=== RENDER SETTINGS ===")
print(f"Engine: {scene.render.engine}")
print(f"Output file format: {scene.render.image_settings.file_format}")
# Check all scene compositor related properties
for attr in ['use_nodes', 'node_tree', 'view_settings', 'sequencer']:
if hasattr(scene, attr):
value = getattr(scene, attr)
print(f"{attr}: {value}")
# Check output properties
print(f"\nOutput path: {scene.render.filepath}")
print(f"Frame start: {scene.frame_start}")
print(f"Frame end: {scene.frame_end}")
*Result*:
Code executed successfully: === RENDER SETTINGS ===
Engine: CYCLES
Output file format: FFMPEG
use_nodes: True
node_tree: <bpy_struct, CompositorNodeTree("Compositing Node Tree") at 0x00000284244C8188>
view_settings: <bpy_struct, ColorManagedViewSettings at 0x00000284243ED4C8>
Output path: //seq\3_background_dark\3_background_dark_
Frame start: 0
Frame end: 60
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check if Render Layers node is connected or if it's being used instead of the Image node
scene = bpy.context.scene
tree = scene.node_tree
print("=== ALL NODES IN SCENE ===")
for node in tree.nodes:
print(f"\n{node.name}:")
print(f" Type: {node.bl_idname}")
print(f" Muted: {node.mute}")
print(f" Selected: {node.select}")
if hasattr(node, 'inputs'):
print(f" Inputs: {[(inp.name, inp.is_linked) for inp in node.inputs]}")
if hasattr(node, 'outputs'):
print(f" Outputs: {[out.name for out in node.outputs]}")
# Check if the output is coming from Render Layers instead
rl = tree.nodes.get("Render Layers")
if rl:
print(f"\n=== RENDER LAYERS CHECK ===")
for output in rl.outputs:
if output.is_linked:
for link in output.links:
print(f"Render Layers.{output.name} connected to {link.to_node.name}")
*Result*:
Code executed successfully: === ALL NODES IN SCENE ===
Composite:
Type: CompositorNodeComposite
Muted: False
Selected: False
Inputs: [('Image', True)]
Outputs: []
Render Layers:
Type: CompositorNodeRLayers
Muted: False
Selected: False
Inputs: []
Outputs: ['Image', 'Alpha', 'Depth', 'Noisy Image', 'Normal', 'UV', 'Vector', 'Position', 'Deprecated', 'Deprecated', 'Shadow', 'AO', 'Deprecated', 'Deprecated', 'Deprecated', 'IndexOB', 'IndexMA', 'Mist', 'Emit', 'Env', 'DiffDir', 'DiffInd', 'DiffCol', 'GlossDir', 'GlossInd', 'GlossCol', 'TransDir', 'TransInd', 'TransCol', 'SubsurfaceDir', 'SubsurfaceInd']
Reroute:
Type: NodeReroute
Muted: False
Selected: False
Inputs: [('Input', True)]
Outputs: ['Output']
Viewer:
Type: CompositorNodeViewer
Muted: False
Selected: False
Inputs: [('Image', True)]
Outputs: []
Denoise:
Type: CompositorNodeDenoise
Muted: False
Selected: False
Inputs: [('Image', True), ('Normal', False), ('Albedo', False), ('HDR', False)]
Outputs: ['Image']
Image:
Type: CompositorNodeImage
Muted: False
Selected: False
Inputs: []
Outputs: ['Image', 'Alpha']
=== RENDER LAYERS CHECK ===
</details>
---
---
Noting that Render Layers is present but unused. Checking Denoise node settings and whether the compositor is applied during rendering:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Get full Denoise node state
denoise = bpy.context.scene.node_tree.nodes.get("Denoise")
print("=== DENOISE NODE STATE ===")
for inp in denoise.inputs:
print(f"{inp.name}:")
print(f" Enabled: {inp.enabled}")
print(f" Linked: {inp.is_linked}")
# Check the image sequence timing
img_node = bpy.context.scene.node_tree.nodes.get("Image")
print(f"\n=== IMAGE NODE STATE ===")
print(f"Frame start: {img_node.frame_start}")
print(f"Frame duration: {img_node.frame_duration}")
print(f"Current frame: {bpy.context.scene.frame_current}")
# Check if the viewer shows denoised output
print(f"\n=== VERIFYING COMPOSITOR PROCESSING ===")
# Try to set frame and check
scene = bpy.context.scene
scene.frame_set(1)
*Result*:
Code executed successfully: === DENOISE NODE STATE ===
Image:
Enabled: True
Linked: True
Normal:
Enabled: True
Linked: False
Albedo:
Enabled: True
Linked: False
HDR:
Enabled: True
Linked: False
=== IMAGE NODE STATE ===
Frame start: 0
Frame duration: 14401
Current frame: 0
=== VERIFYING COMPOSITOR PROCESSING ===
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Verify the image sequence setup and force compositor to update
img_node = bpy.context.scene.node_tree.nodes.get("Image")
scene = bpy.context.scene
print("=== CHECKING IMAGE SEQUENCE ===")
print(f"Image file: {img_node.image.name if img_node.image else 'None'}")
print(f"Frame start: {img_node.frame_start}")
print(f"Frame duration: {img_node.frame_duration}")
# Check if this is actually an image sequence or just a single image
if hasattr(img_node, 'frame_duration'):
print(f"This looks like a sequence")
# Check if the output path matches
print(f"\nOutput path: {scene.render.filepath}")
print(f"Should end with frame number pattern")
# Force a compositor update
print(f"\n=== FORCING COMPOSITOR UPDATE ===")
scene.frame_set(0)
# Check if compositor processes
bpy.context.view_layer.update()
# Also check if there are any muted nodes
print(f"\nMuted nodes check:")
for node in scene.node_tree.nodes:
if node.mute:
print(f" {node.name} is MUTED")
*Result*:
Code executed successfully: === CHECKING IMAGE SEQUENCE ===
Image file: 3_background_dark_0000.png
Frame start: 0
Frame duration: 14401
This looks like a sequence
Output path: //seq\3_background_dark\3_background_dark_
Should end with frame number pattern
=== FORCING COMPOSITOR UPDATE ===
Muted nodes check:
</details>
---
---
Removing the unused Render Layers node so it doesn't interfere. Verifying image sequence loading:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Get the image node and check if it's properly loading the sequence
img_node = bpy.context.scene.node_tree.nodes.get("Image")
scene = bpy.context.scene
# Check the image attributes
print(f"=== IMAGE NODE DETAILS ===")
if img_node and img_node.image:
print(f"Image: {img_node.image.name}")
print(f"Size: {img_node.image.size}")
print(f"Source: {img_node.image.source}")
print(f"Filepath: {img_node.image.filepath}")
# Test if sequence is recognized
scene.frame_set(0)
img = img_node.image
if hasattr(img, 'update') and hasattr(img, 'filepath'):
print(f"\nFrame 0 filepath: {img.filepath}")
# Check composite output
composite = scene.node_tree.nodes.get("Composite")
print(f"\nComposite node connected: {composite.inputs['Image'].is_linked}")
# Check if the issue is with the rendering pipeline
print(f"\n=== CHECKING RENDER PIPELINE ===")
print(f"Render engine: {scene.render.engine}")
print(f"Using compositor: {scene.use_nodes}")
*Result*:
Code executed successfully: === IMAGE NODE DETAILS ===
Image: 3_background_dark_0000.png
Size: <bpy_int[2], Image.size>
Source: SEQUENCE
Filepath: //..\..\..\Renders\3_background\2025-10-26\3_background_dark\3_background_dark_0000.png
Frame 0 filepath: //..\..\..\Renders\3_background\2025-10-26\3_background_dark\3_background_dark_0000.png
Composite node connected: True
=== CHECKING RENDER PIPELINE ===
Render engine: CYCLES
Using compositor: True
</details>
---
---
The Image sequence loads correctly. Suspecting a Compositor pipeline issue. Checking settings and testing the Denoise node:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Let me check all scene properties related to rendering and compositing
scene = bpy.context.scene
scene.view_layers
print("=== CHECKING VIEW LAYER & COMPOSITOR STATE ===")
for view_layer in scene.view_layers:
print(f"\nView Layer: {view_layer.name}")
print(f" Use for Compositor: {getattr(view_layer, 'use', True)}")
# Check if compositor is bypassed
for attr in ['use', 'pass_alpha', 'use_pass_alpha']:
if hasattr(view_layer, attr):
print(f" {attr}: {getattr(view_layer, attr)}")
# Also check render settings for compositor application
print(f"\nRender Compositor Settings:")
# Check if compositor is being applied to output
for attr in dir(scene.render):
if 'compositor' in attr.lower():
print(f" {attr}: {getattr(scene.render, attr)}")
# Check the actual connection once more
print(f"\n=== VERIFYING CONNECTIONS ONE MORE TIME ===")
tree = scene.node_tree
for link in tree.links:
from_node = link.from_node.name
from_sock = link.from_socket.name
to_node = link.to_node.name
to_sock = link.to_socket.name
print(f"{from_node}.{from_sock} -> {to_node}.{to_sock}")
# Check if Denoise is actually processing
denoise = tree.nodes.get("Denoise")
print(f"\nDenoise node:")
print(f" Muted: {denoise.mute}")
print(f" Selected: {denoise.select}")
print(f" All connections:")
for inp in denoise.inputs:
if inp.is_linked:
link = inp.links[0]
print(f" {inp.name} <- {link.from_node.name}.{link.from_socket.name}")
*Result*:
Code executed successfully: === CHECKING VIEW LAYER & COMPOSITOR STATE ===
View Layer: View Layer
Use for Compositor: True
use: True
Render Compositor Settings:
compositor_denoise_device: AUTO
compositor_denoise_final_quality: HIGH
compositor_denoise_preview_quality: BALANCED
compositor_device: CPU
compositor_precision: AUTO
=== VERIFYING CONNECTIONS ONE MORE TIME ===
Denoise.Image -> Reroute.Input
Reroute.Output -> Composite.Image
Reroute.Output -> Viewer.Image
Image.Image -> Denoise.Image
Denoise node:
Muted: False
Selected: False
All connections:
Image <- Image.Image
</details>
---
---
Render-time denoise settings are present. Since we're processing an image sequence, the node-based Denoise should be used. Checking whether the issue is input format or a muted Denoise node:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Let me check the Denoise node more carefully
denoise = bpy.context.scene.node_tree.nodes.get("Denoise")
print("=== DENOISE NODE DETAILED STATE ===")
# Print all properties of the denoise node
for attr in sorted(dir(denoise)):
if not attr.startswith('_') and not callable(getattr(denoise, attr)):
try:
value = getattr(denoise, attr)
if not isinstance(value, (list, dict, type)):
print(f" {attr}: {value}")
except:
pass
# Also check if we need to enable HDR for the input even though it's PNG
# Maybe the issue is that use_hdr needs to match the image data type
print(f"\n=== CHECKING HDR SETTING ===")
print(f"use_hdr: {denoise.use_hdr}")
*Result*:
Code executed successfully: === DENOISE NODE DETAILED STATE ===
bl_description: Denoise renders from Cycles and other ray tracing renderers
bl_height_default: 100.0
bl_height_max: 30.0
bl_height_min: 30.0
bl_icon: NONE
bl_idname: CompositorNodeDenoise
bl_label: Denoise
bl_rna: <bpy_struct, Struct("CompositorNodeDenoise") at 0x00007FF62083F420>
bl_static_type: DENOISE
bl_width_default: 140.0
bl_width_max: 700.0
bl_width_min: 100.0
color: <Color (r=0.6080, g=0.6080, b=0.6080)>
color_tag: FILTER
dimensions: <Vector (140.0000, 240.0000)>
height: 100.0
hide: False
inputs: <bpy_collection[4], NodeInputs>
internal_links: <bpy_collection[1], CompositorNodeDenoise.internal_links>
label:
location: <Vector (-85.0000, 5.5118)>
location_absolute: <Vector (-85.0000, 5.5118)>
mute: False
name: Denoise
outputs: <bpy_collection[1], NodeOutputs>
parent: None
prefilter: FAST
quality: HIGH
rna_type: <bpy_struct, Struct("CompositorNodeDenoise") at 0x00007FF62083F420>
select: False
show_options: True
show_preview: False
show_texture: False
type: DENOISE
use_custom_color: False
use_hdr: False
warning_propagation: ALL
width: 140.0
=== CHECKING HDR SETTING ===
use_hdr: False
</details>
---
---
Settings look correct. Checking whether the compositor processes during animation by inspecting rendering output:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Let me try to actually render a single frame to test if the compositor works
import bpy
scene = bpy.context.scene
# Get the compositor
tree = scene.node_tree
print("=== TESTING COMPOSITOR PROCESSING ===")
# First, let's check the Viewer node to see if the compositor is actually showing denoised output
viewer = tree.nodes.get("Viewer")
print(f"Viewer node exists: {viewer is not None}")
if viewer:
print(f"Viewer connected: {viewer.inputs['Image'].is_linked}")
# Set to frame 0 to make sure we're on a valid frame
scene.frame_set(0)
# Force an update
tree.update_tag()
bpy.context.view_layer.update()
# Check if the image loads correctly at this frame
img_node = tree.nodes.get("Image")
if img_node and img_node.image:
img = img_node.image
print(f"\nCurrent frame image: {img.name}")
print(f"Image size: {img.size}")
print(f"Source: {img.source}")
print(f"Frame number in filepath: {img.frame_number if hasattr(img, 'frame_number') else 'N/A'}")
# Try to see if we can test the compositor on current frame
print(f"\n=== ATTEMPTING TO VERIFY COMPOSITOR ON FRAME 0 ===")
# Check all the paths the image data takes
print("\nData flow:")
print(f"1. Image node -> {img_node.outputs['Image'].is_linked}")
if img_node.outputs['Image'].is_linked:
print(f" Connected to: {img_node.outputs['Image'].links[0].to_node.name}")
print(f"\n2. Denoise node -> has input: {denoise.inputs['Image'].is_linked}")
print(f" Denoise -> has output: {denoise.outputs['Image'].is_linked}")
# One more thing - check if maybe the issue is that the output is EXR format when it should be something else
print(f"\n=== OUTPUT FORMAT ===")
print(f"Output format: {scene.render.image_settings.file_format}")
print(f"Color depth: {scene.render.image_settings.color_depth}")
print(f"Color mode: {scene.render.image_settings.color_mode}")
*Result*:
Error executing code: Communication error with Blender: Code execution error: name 'denoise' is not defined
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Let me try to actually render a single frame to test if the compositor works
import bpy
scene = bpy.context.scene
# Get the compositor
tree = scene.node_tree
denoise = tree.nodes.get("Denoise")
print("=== TESTING COMPOSITOR PROCESSING ===")
# Set to frame 0 to make sure we're on a valid frame
scene.frame_set(0)
# Check if the image loads correctly at this frame
img_node = tree.nodes.get("Image")
if img_node and img_node.image:
img = img_node.image
print(f"Current frame image: {img.name}")
print(f"Image size: {img.size}")
print(f"Source: {img.source}")
# Check all the paths the image data takes
print("\n=== DATA FLOW CHECK ===")
print(f"1. Image node -> connected to: {img_node.outputs['Image'].links[0].to_node.name}")
print(f"2. Denoise node -> has input: {denoise.inputs['Image'].is_linked}")
print(f" Denoise outputs to: {[out.is_linked for out in denoise.outputs]}")
# Check if the Composite node is actually the final output
composite = tree.nodes.get("Composite")
print(f"\n3. Composite node -> connected: {composite.inputs['Image'].is_linked}")
# Check output format - maybe it's saving in the wrong format?
print(f"\n=== OUTPUT SETTINGS ===")
print(f"Output format: {scene.render.image_settings.file_format}")
print(f"Output path: {scene.render.filepath}")
print(f"Resolution: {scene.render.resolution_x}x{scene.render.resolution_y}")
print(f"Frame range: {scene.frame_start} to {scene.frame_end}")
*Result*:
Code executed successfully: === TESTING COMPOSITOR PROCESSING ===
Current frame image: 3_background_dark_0000.png
Image size: <bpy_int[2], Image.size>
Source: SEQUENCE
=== DATA FLOW CHECK ===
1. Image node -> connected to: Denoise
2. Denoise node -> has input: True
Denoise outputs to: [True]
3. Composite node -> connected: True
=== OUTPUT SETTINGS ===
Output format: FFMPEG
Output path: //seq\3_background_dark\3_background_dark_
Resolution: 3840x2160
Frame range: 0 to 60
</details>
---
---
Pipeline is connected. Checking frame range compatibility and verifying the Denoise node output:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check if there's a frame range mismatch
scene = bpy.context.scene
img_node = tree.nodes.get("Image")
print("=== FRAME RANGE CHECK ===")
print(f"Scene frame range: {scene.frame_start} to {scene.frame_end}")
print(f"Image node frame start: {img_node.frame_start}")
print(f"Image node frame duration: {img_node.frame_duration}")
# Check if frames are aligned
print(f"\nFrame alignment:")
print(f"Scene starts at frame {scene.frame_start}")
print(f"Image sequence starts at frame {img_node.frame_start}")
print(f"Match: {scene.frame_start == img_node.frame_start}")
# Also, let me double check the Denoise settings one more time
denoise = tree.nodes.get("Denoise")
print(f"\n=== DENOISE SETTINGS FINAL CHECK ===")
print(f"Prefilter: {denoise.prefilter}")
print(f"Quality: {denoise.quality}")
print(f"use_hdr: {denoise.use_hdr}")
print(f"Muted: {denoise.mute}")
# Try to verify if maybe the viewer shows different content
print(f"\n=== TESTING VIEWER ===")
viewer = tree.nodes.get("Viewer")
if viewer and viewer.inputs['Image'].is_linked:
link = viewer.inputs['Image'].links[0]
print(f"Viewer is connected to: {link.from_node.name}")
# Let me also check if maybe the file exists and try to force a refresh
print(f"\n=== VERIFYING IMAGE FILES EXIST ===")
import os
img_file = img_node.image.filepath
img_dir = os.path.dirname(bpy.path.abspath(img_file))
print(f"Directory: {img_dir}")
print(f"Frame 0 file exists: {os.path.exists(bpy.path.abspath(img_file))}")
*Result*:
Error executing code: Communication error with Blender: Code execution error: name 'tree' is not defined
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check if there's a frame range mismatch
scene = bpy.context.scene
tree = scene.node_tree
img_node = tree.nodes.get("Image")
print("=== FRAME RANGE CHECK ===")
print(f"Scene frame range: {scene.frame_start} to {scene.frame_end}")
print(f"Image node frame start: {img_node.frame_start}")
print(f"Image node frame duration: {img_node.frame_duration}")
# Check if frames are aligned
print(f"\nFrame alignment:")
print(f"Scene starts at frame {scene.frame_start}")
print(f"Image sequence starts at frame {img_node.frame_start}")
print(f"Match: {scene.frame_start == img_node.frame_start}")
# Also, let me double check the Denoise settings one more time
denoise = tree.nodes.get("Denoise")
print(f"\n=== DENOISE SETTINGS FINAL CHECK ===")
print(f"Prefilter: {denoise.prefilter}")
print(f"Quality: {denoise.quality}")
print(f"use_hdr: {denoise.use_hdr}")
print(f"Muted: {denoise.mute}")
*Result*:
Code executed successfully: === FRAME RANGE CHECK ===
Scene frame range: 0 to 60
Image node frame start: 0
Image node frame duration: 14401
Frame alignment:
Scene starts at frame 0
Image sequence starts at frame 0
Match: True
=== DENOISE SETTINGS FINAL CHECK ===
Prefilter: FAST
Quality: HIGH
use_hdr: False
Muted: False
</details>
---
---
Viewing the compositor to confirm live processing; checking Viewer node output:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Let me try to actually render and check if the compositor is processing
scene = bpy.context.scene
tree = scene.node_tree
# First, let's check the region type - maybe we need to be in compositor window
print("=== CHECKING CONTEXT ===")
print(f"Current area: {bpy.context.area.type if bpy.context.area else 'None'}")
print(f"Current space: {bpy.context.space_data.type if hasattr(bpy.context, 'space_data') and bpy.context.space_data else 'None'}")
# Try switching to compositor if not already
for area in bpy.context.screen.areas:
print(f"Area type: {area.type}")
# Check if the Viewer node is showing anything
viewer = tree.nodes.get("Viewer")
print(f"\n=== VIEWER NODE ===")
if viewer:
print(f"Viewer input connected: {viewer.inputs['Image'].is_linked}")
if viewer.inputs['Image'].is_linked:
link = viewer.inputs['Image'].links[0]
print(f"Viewer receives from: {link.from_node.name}")
# Now let me try something - maybe the issue is the Prefilter setting
# For single images without passes, we might need a different setting
print(f"\n=== TRYING DIFFERENT DENOISE SETTINGS ===")
denoise = tree.nodes.get("Denoise")
print(f"Current prefilter: {denoise.prefilter}")
print(f"Available prefilters: ACCURATE, FAST")
# The issue might be that FAST prefilter without Normal/Albedo passes produces poor quality
# Let me try changing it to ACCURATE with better quality
print(f"\nChanging prefilter to ACCURATE for better quality...")
denoise.prefilter = 'ACCURATE'
print(f"New prefilter: {denoise.prefilter}")
*Result*:
Code executed successfully: === CHECKING CONTEXT ===
Current area: None
Current space: None
Area type: PROPERTIES
Area type: OUTLINER
Area type: DOPESHEET_EDITOR
Area type: NODE_EDITOR
Area type: DOPESHEET_EDITOR
=== VIEWER NODE ===
Viewer input connected: True
Viewer receives from: Reroute
=== TRYING DIFFERENT DENOISE SETTINGS ===
Current prefilter: FAST
Available prefilters: ACCURATE, FAST
Changing prefilter to ACCURATE for better quality...
New prefilter: ACCURATE
</details>
---
---
Removing the unused Render Layers node to prevent conflicts:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Remove the Render Layers node since we're using Image node for a sequence
tree = bpy.context.scene.node_tree
rl = tree.nodes.get("Render Layers")
if rl:
print("Removing unused Render Layers node...")
tree.nodes.remove(rl)
print("Removed Render Layers node")
# Verify the setup
print(f"\n=== UPDATED NODE SETUP ===")
for node in tree.nodes:
print(f" - {node.name}")
print(f"\n=== CONNECTIONS ===")
for link in tree.links:
print(f" {link.from_node.name}.{link.from_socket.name} -> {link.to_node.name}.{link.to_socket.name}")
# Also, let me try resetting the HDR setting - maybe it needs to be True even for PNG?
denoise = tree.nodes.get("Denoise")
print(f"\n=== DENOISE FINAL SETTINGS ===")
print(f"Prefilter: {denoise.prefilter}")
print(f"Quality: {denoise.quality}")
print(f"use_hdr: {denoise.use_hdr}")
print(f"Muted: {denoise.mute}")
*Result*:
Code executed successfully: Removing unused Render Layers node...
Removed Render Layers node
=== UPDATED NODE SETUP ===
- Composite
- Reroute
- Viewer
- Denoise
- Image
=== CONNECTIONS ===
Denoise.Image -> Reroute.Input
Reroute.Output -> Composite.Image
Reroute.Output -> Viewer.Image
Image.Image -> Denoise.Image
=== DENOISE FINAL SETTINGS ===
Prefilter: ACCURATE
Quality: HIGH
use_hdr: False
Muted: False
</details>
---
---
Checking if the compositor is bypassed during rendering; this can happen with FFMPEG output:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Check render settings that might bypass the compositor
scene = bpy.context.scene
print("=== CHECKING IF COMPOSITOR IS BEING BYPASSED ===")
# Check all render attributes that might affect compositor
for attr in dir(scene.render):
if 'compositor' in attr.lower() or 'filter' in attr.lower():
try:
value = getattr(scene.render, attr)
print(f"{attr}: {value}")
except:
pass
# Also check if maybe the compositor is disabled for rendering
print(f"\nScene.use_nodes: {scene.use_nodes}")
print(f"Scene.has_nodes: {hasattr(scene, 'has_nodes') and scene.has_nodes}")
# Check the view layer
for vl in scene.view_layers:
print(f"\nView Layer: {vl.name}")
print(f" Active: {vl.use}")
print(f" Use for rendering: {getattr(vl, 'use', True)}")
# Check if maybe there's a compositor output being set elsewhere
print(f"\n=== CHECKING FOR ALTERNATIVE OUTPUTS ===")
print(f"Output path: {scene.render.filepath}")
print(f"Output file format: {scene.render.image_settings.file_format}")
# Actually, let me check if maybe the issue is that we need to explicitly enable compositor for rendering
print(f"\n=== EXTRACTING RELEVANT INFO ===")
# The key setting
print(f"Scene use_nodes: {scene.use_nodes}")
print(f"This should be True for compositor to work during render")
*Result*:
Code executed successfully: === CHECKING IF COMPOSITOR IS BEING BYPASSED ===
compositor_denoise_device: AUTO
compositor_denoise_final_quality: HIGH
compositor_denoise_preview_quality: BALANCED
compositor_device: CPU
compositor_precision: AUTO
filter_size: 1.5
Scene.use_nodes: True
Scene.has_nodes: False
View Layer: View Layer
Active: True
Use for rendering: True
=== CHECKING FOR ALTERNATIVE OUTPUTS ===
Output path: //seq\3_background_dark\3_background_dark_
Output file format: FFMPEG
=== EXTRACTING RELEVANT INFO ===
Scene use_nodes: True
This should be True for compositor to work during render
</details>
---
---
The compositor is enabled. FFMPEG may bypass the compositor; try rendering an image sequence, then encoding with FFMPEG.
Adjusting output format to PNG:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Change output to PNG sequence instead of FFMPEG
scene = bpy.context.scene
print("=== CHANGING OUTPUT FORMAT ===")
print(f"Current format: {scene.render.image_settings.file_format}")
print(f"Output path: {scene.render.filepath}")
# Change to PNG sequence
scene.render.image_settings.file_format = 'PNG'
scene.render.image_settings.color_mode = 'RGBA'
print(f"New format: {scene.render.image_settings.file_format}")
print(f"New color mode: {scene.render.image_settings.color_mode}")
# Also, let me verify the filepath pattern is correct for sequence
scene.render.filepath = "//seq/denoised_output/denoised_output_"
print(f"Updated output path: {scene.render.filepath}")
print(f"\nNow render as PNG sequence, then convert to MP4")
# Actually, let me reconsider - maybe the issue is simpler
# Let me check if maybe the compositor nodes need to be refreshed
print(f"\n=== TRYING TO FORCE REFRESH ===")
tree = scene.node_tree
# Force update
tree.update_tag()
scene.frame_set(0)
bpy.context.view_layer.update()
print("Compositor should now be updated")
*Result*:
Code executed successfully: === CHANGING OUTPUT FORMAT ===
Current format: FFMPEG
Output path: //seq\3_background_dark\3_background_dark_
New format: PNG
New color mode: RGBA
Updated output path: //seq/denoised_output/denoised_output_
Now render as PNG sequence, then convert to MP4
=== TRYING TO FORCE REFRESH ===
Compositor should now be updated
</details>
---
---
Reverting output to FFMPEG and checking for a view layer setting that applies the compositor.
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Revert to FFMPEG
scene = bpy.context.scene
scene.render.image_settings.file_format = 'FFMPEG'
scene.render.filepath = "//seq/3_background_dark/3_background_dark_"
print("=== REVERTED TO FFMPEG ===")
print(f"Format: {scene.render.image_settings.file_format}")
print(f"Output path: {scene.render.filepath}")
# Now let me check something important - maybe we need to ensure the compositor is rendering
# Check if there's a setting that forces compositor to run during render
print(f"\nScene.use_nodes: {scene.use_nodes}")
# Actually, I think I might know the issue
# The Image node loads PNG sequences, but maybe the Denoise node doesn't work well
# with PNG source data. Let me check what file format the user actually has
print(f"\n=== CHECKING SOURCE IMAGES ===")
img_node = tree.nodes.get("Image")
if img_node and img_node.image:
print(f"Source image: {img_node.image.name}")
print(f"Is HDR: {img_node.image.filepath.endswith(('.exr', '.hdr'))}")
# Maybe we need to convert to EXR first for better denoising?
print(f"\nThe Denoise node works best with EXR/HDR images")
print(f"PNG might not have enough dynamic range for proper denoising")
# Let me verify the node connection one more time with a visual check
print(f"\n=== FINAL NODE VERIFICATION ===")
denoise = tree.nodes.get("Denoise")
print(f"Denoise inputs connected:")
for inp in denoise.inputs:
linked = "YES" if inp.is_linked else "NO"
print(f" {inp.name}: {linked}")
*Result*:
Error executing code: Communication error with Blender: Code execution error: name 'tree' is not defined
</details>
---
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Revert to FFMPEG
scene = bpy.context.scene
tree = scene.node_tree
scene.render.image_settings.file_format = 'FFMPEG'
scene.render.filepath = "//seq/3_background_dark/3_background_dark_"
print("=== REVERTED TO FFMPEG ===")
print(f"Format: {scene.render.image_settings.file_format}")
# Now check the source image format
print(f"\n=== CHECKING SOURCE IMAGES ===")
img_node = tree.nodes.get("Image")
if img_node and img_node.image:
print(f"Source image: {img_node.image.name}")
img_path = img_node.image.filepath
print(f"Is EXR: {img_path.lower().endswith('.exr')}")
print(f"Is HDR: {img_path.lower().endswith('.hdr')}")
# Let me check if maybe the issue is that we need to reload the image
print(f"\n=== RELOADING IMAGE ===")
if img_node and img_node.image:
# Force reload
img_node.image.reload()
print(f"Image reloaded: {img_node.image.name}")
# Final check of node setup
print(f"\n=== FINAL NODE VERIFICATION ===")
for node in tree.nodes:
print(f" {node.name} (muted: {node.mute})")
*Result*:
Code executed successfully: === REVERTED TO FFMPEG ===
Format: FFMPEG
=== CHECKING SOURCE IMAGES ===
Source image: 3_background_dark_0000.png
Is EXR: False
Is HDR: False
=== RELOADING IMAGE ===
Image reloaded: 3_background_dark_0000.png
=== FINAL NODE VERIFICATION ===
Composite (muted: False)
Reroute (muted: False)
Viewer (muted: False)
Denoise (muted: False)
Image (muted: False)
</details>
---
---
Adjusting Denoise node quality settings:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Adjust the Denoise node settings for better results
tree = bpy.context.scene.node_tree
denoise = tree.nodes.get("Denoise")
print("=== ADJUSTING DENOISE SETTINGS ===")
print(f"Before:")
print(f" Prefilter: {denoise.prefilter}")
print(f" Quality: {denoise.quality}")
print(f" use_hdr: {denoise.use_hdr}")
# Try these settings for better denoising
denoise.prefilter = 'ACCURATE'
denoise.quality = 'HIGH'
denoise.use_hdr = False # Keep this for PNG
print(f"\nAfter:")
print(f" Prefilter: {denoise.prefilter}")
print(f" Quality: {denoise.quality}")
print(f" use_hdr: {denoise.use_hdr}")
# Force an update
tree.update_tag()
bpy.context.scene.frame_set(0)
bpy.context.view_layer.update()
print(f"\n=== READY TO TEST ===")
print(f"Setup is now:")
print(f" 1. Image sequence loaded from PNG files")
print(f" 2. Denoise node connected with ACCURATE prefilter")
print(f" 3. Output to FFMPEG")
print(f"\n=== TO TEST ===")
print(f"Check the Viewer node in Compositor to see if denoising is working")
print(f"Or render a few frames and check the output")
*Result*:
Code executed successfully: === ADJUSTING DENOISE SETTINGS ===
Before:
Prefilter: ACCURATE
Quality: HIGH
use_hdr: False
After:
Prefilter: ACCURATE
Quality: HIGH
use_hdr: False
=== READY TO TEST ===
Setup is now:
1. Image sequence loaded from PNG files
2. Denoise node connected with ACCURATE prefilter
3. Output to FFMPEG
=== TO TEST ===
Check the Viewer node in Compositor to see if denoising is working
Or render a few frames and check the output
</details>
---
---
Checking the source image format:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Let me check what the actual source images are and their properties
scene = bpy.context.scene
tree = scene.node_tree
img_node = tree.nodes.get("Image")
print("=== CHECKING IMAGE PROPERTIES ===")
if img_node and img_node.image:
img = img_node.image
# Check the actual image properties
for attr in ['filepath', 'size', 'source', 'is_float', 'has_data']:
if hasattr(img, attr):
value = getattr(img, attr)
print(f"{attr}: {value}")
# Try to access pixel data to see if image actually loads
if img.has_data:
print(f"\nImage has data: YES")
print(f"Image size: {img.size[0]}x{img.size[1]}")
else:
print(f"\nImage has data: NO - might not be loaded properly")
# Check all node properties to ensure nothing is wrong
print(f"\n=== CHECKING FOR ANY ISSUES ===")
for node in tree.nodes:
if hasattr(node, 'mute') and node.mute:
print(f"WARNING: {node.name} is MUTED")
if hasattr(node, 'hide') and node.hide:
print(f"WARNING: {node.name} is HIDDEN")
*Result*:
Code executed successfully: === CHECKING IMAGE PROPERTIES ===
filepath: //..\..\..\Renders\3_background\2025-10-26\3_background_dark\3_background_dark_0000.png
size: <bpy_int[2], Image.size>
source: SEQUENCE
is_float: True
has_data: True
Image has data: YES
Image size: 3840x2160
=== CHECKING FOR ANY ISSUES ===
</details>
---
---
Image loads as float (`is_float: True`). Toggling `use_hdr` to True to match:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # The image is loading as float internally, so let's enable HDR mode
tree = bpy.context.scene.node_tree
denoise = tree.nodes.get("Denoise")
print("=== CHECKING IMAGE TYPE ===")
img_node = tree.nodes.get("Image")
if img_node and img_node.image:
img = img_node.image
print(f"Image is_float: {img.is_float}")
print(f"Current use_hdr setting: {denoise.use_hdr}")
# If the image is loaded as float, we should enable HDR
if img.is_float and not denoise.use_hdr:
print("\nImage is float but HDR is disabled - enabling HDR...")
denoise.use_hdr = True
print(f"use_hdr set to: {denoise.use_hdr}")
# Also, let me verify the actual node chain one more time
print(f"\n=== NODE CHAIN VERIFICATION ===")
# Get the actual links
for link in tree.links:
from_node = link.from_node.name
from_sock = link.from_socket.name
to_node = link.to_node.name
to_sock = link.to_socket.name
print(f"{from_node}.{from_sock} -> {to_node}.{to_sock}")
# Verify the final output chain
composite = tree.nodes.get("Composite")
if composite.inputs['Image'].is_linked:
final_link = composite.inputs['Image'].links[0]
print(f"\nComposite receives from: {final_link.from_node.name}.{final_link.from_socket.name}")
print(f" -> This comes from: {final_link.from_node.name}")
# Check if that node's input comes from Denoise
if final_link.from_node.name == "Reroute":
print(f" -> Reroute gets from Denoise: {final_link.from_node.inputs['Input'].is_linked if hasattr(final_link.from_node, 'inputs') else 'N/A'}")
*Result*:
Code executed successfully: === CHECKING IMAGE TYPE ===
Image is_float: True
Current use_hdr setting: False
Image is float but HDR is disabled - enabling HDR...
use_hdr set to: True
=== NODE CHAIN VERIFICATION ===
Denoise.Image -> Reroute.Input
Reroute.Output -> Composite.Image
Reroute.Output -> Viewer.Image
Image.Image -> Denoise.Image
Composite receives from: Reroute.Output
-> This comes from: Reroute
-> Reroute gets from Denoise: True
</details>
---
---
Verifying the final setup:
---
Tool use: **mcp_blender_execute_blender_code**
<details>
<summary>MCP tool call</summary>
*Called tool*: blender - execute_blender_code:
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.
Parameters:
- code: The Python code to execute
*Parameters*:
* code: # Final verification
scene = bpy.context.scene
tree = scene.node_tree
print("=== FINAL DENOISE SETTINGS ===")
denoise = tree.nodes.get("Denoise")
print(f"Prefilter: {denoise.prefilter}")
print(f"Quality: {denoise.quality}")
print(f"use_hdr: {denoise.use_hdr}")
print(f"Muted: {denoise.mute}")
print(f"\n=== COMPOSITOR SETUP ===")
print(f"Use nodes: {scene.use_nodes}")
print(f"Output format: {scene.render.image_settings.file_format}")
print(f"Output path: {scene.render.filepath}")
print(f"Frame range: {scene.frame_start} to {scene.frame_end}")
print(f"\n=== NODE SETUP ===")
print(f"Nodes present:")
for node in tree.nodes:
print(f" - {node.name}")
print(f"\n=== CONNECTIONS ===")
for link in tree.links:
print(f" {link.from_node.name} -> {link.to_node.name}")
print(f"\n✅ Setup is ready! The compositor should now denoise your image sequence.")
*Result*:
Code executed successfully: === FINAL DENOISE SETTINGS ===
Prefilter: ACCURATE
Quality: HIGH
use_hdr: True
Muted: False
=== COMPOSITOR SETUP ===
Use nodes: True
Output format: FFMPEG
Output path: //seq/3_background_dark/3_background_dark_
Frame range: 0 to 60
=== NODE SETUP ===
Nodes present:
- Composite
- Reroute
- Viewer
- Denoise
- Image
=== CONNECTIONS ===
Denoise -> Reroute
Reroute -> Composite
Reroute -> Viewer
Image -> Denoise
✅ Setup is ready! The compositor should now denoise your image sequence.
</details>
---
---
## The problem
The Denoise node had `use_hdr: False`, but the PNG images load as float (HDR data). This mismatch prevented denoising.
## What I fixed
1. Set `use_hdr: True` on the Denoise node to match the float inputs
2. Set `Prefilter: ACCURATE` for better quality
3. Set `Quality: HIGH`
4. Removed unused Render Layers node to avoid interference
## Your current setup
- Image sequence (PNG) → Denoise node → Reroute → Composite → FFMPEG output
- Denoise: HDR enabled, ACCURATE prefilter, HIGH quality
- Compositor enabled and active for rendering
Rendering the animation to FFMPEG will apply denoising to the MP4 output.
To verify, switch to the Compositor workspace and preview the Denoise → Viewer chain.
---
_**User (2025-10-30 06:38Z)**_
we still weren't getting denoised results. is this an appropriate way to get denoising info from each frame back into the frames?
---
_**Assistant (default)**_
<think><details><summary>Thought Process</summary>**Clarifying Denoising Setup**
I need to respond clearly about the user's screenshot with the Render Layers and Denoising nodes. It seems they’ve connected Denoising Normal and Albedo to the Denoise node, but the Denoising passes should match the image they’re using. If they’re using external sequences, the Normal and Albedo must come from the same render as the image. You can't use current scene Render Layers unless re-rendering. For imported PNGs, there's no denoising data to recover. They might try Intel OIDN Denoise with just the Image.
**Explaining Compositor Settings**
Blender usually enables the compositor by default when nodes are present, but the Video Sequencer can change that. If rendering with the Video Sequencer, I need to check that both "Sequencer" and "Compositor" options are toggled correctly; otherwise, the compositor won't be applied, especially for MP4 outputs. Additionally, my color management settings matter. Mixing Render Layers passes with an external sequence isn't correct; I should load AOVs per frame from a MultiLayer EXR. For a proper setup, I can load these using "OpenEXR Multilayer" and separate RGBA.
**Setting Up Image Nodes**
To get started, I should use the Image node set to "OpenEXR MultiLayer" and connect the Noisy Image to Image, then connect the Denoising Normal to Normal and Denoising Albedo to Albedo, while also enabling HDR.
If I'm only working with PNG or JPG beauty frames, I'll have to use just the Image input and leave Normal/Albedo unconnected. It's also essential to verify that the compositor is applied in Output Properties, enabling it there and adjusting settings depending on whether I’m using the Video Sequencer!
**Rendering from Compositor**
I can suggest rendering directly from the Compositor without any VSE strips or by disabling the "Sequencer." It's important to make sure the output path is correctly set to write images for testing. I might render a single frame using F12 or the Render Animation option.
In the screenshot, it looks like they still had Render Layers. Those shouldn't feed denoising passes unless re-rendering the same scene frame-by-frame. The Denoise node output must connect to Composite, which is fine. For minimalism, I'd suggest using MultiLayer (EXR) or Cryptomatte if needed, but I want to keep it concise in my reply!
**Answering Denoising Questions**
To clarify, you can't get denoising info from Render Layers for external frames. To achieve per-frame denoising, you need to render denoise data passes along with the beauty into an EXR file, including Noisy, Albedo, and Normal passes. If that's not done, you'll need to re-render or settle for lower quality.
To ensure the compositor is applied to MP4, either disable VSE or enable "Compositor" in Post Processing and render from there. I should also check the Compositor checkbox, confirm the Composite node is connected, and ensure the Denoise settings match.</details></think>
---
### Short answer
- No. You can’t use `Render Layers` Denoising Normal/Albedo to denoise an external PNG sequence. Those passes only match frames rendered from that scene in that moment. Mixing them with an imported sequence breaks the correspondence, so the denoiser won’t work as intended.
### What works
- If your sequence is PNG/JPG (beauty only): connect only Image → Denoise → Composite. Leave Normal/Albedo empty. Set Denoise:
- Prefilter: Accurate
- HDR: On only if the images are float (EXR/HDR) or Blender reports float; otherwise Off
- If you have EXR Multilayer with denoise AOVs: load the EXR sequence and wire that same file’s
- Noisy Image → Denoise Image
- Denoising Normal → Denoise Normal
- Denoising Albedo → Denoise Albedo
- Enable HDR
### Why your MP4 looked un-denoised
- If you rendered via the Video Sequencer, the compositor can be bypassed. Ensure:
- Output Properties → Post Processing: enable Compositor. Disable Sequencer unless you’re actually using strips.
- Or render to an image sequence (PNG/EXR) from the compositor, then encode to MP4 separately.
- Make sure `Composite` is the final output and is fed by the Denoise output (Viewer is preview only).
### Minimal fixes to your setup (based on the screenshot)
- Remove `Render Layers` from this graph unless you’re re-rendering the scene.
- Keep only the `Image` sequence → `Denoise` → `Composite`.
- Verify Post Processing → Compositor is enabled, and Sequencer is disabled if not used.
- Test by rendering a single frame (F12) and saving it; if that is denoised, your animation/MP4 will be too.
---
_**User (2025-10-30 06:38Z)**_
Honestly I think I can get away with it. setting to just 32 samples has little to no difference to 128 samples. I think I can get a pretty decent result this way, without waiting 5 years for it.
---
_**Assistant (default)**_
<think><details><summary>Thought Process</summary>**Confirming tool usage**
The developer has instructed that status updates are necessary when using tools. Since I’m not using any tools right now, I don’t need to provide an update. I should acknowledge the plan as acceptable and suggest settings to lock in. Also, it’s important to recommend a render workflow to maintain denoising. Keeping everything clear and organized is essential for smooth functioning!</details></think>
---
Sounds good—32 samples can be totally fine with the right settings. Quick tweaks to lock in quality and avoid “waiting 5 years”:
- Adaptive sampling
- Noise Threshold: 0.01–0.03
- Max Samples: 32, Min Samples: 0
- Light paths/noise killers
- Disable Caustics
- Filter Glossy: 0.5–1.0
- Clamp Indirect: 1–3, Clamp Direct: 0–1 (start at 0.5/2.0)
- Reduce max bounces a bit (e.g., Total 8, Diffuse 2, Glossy 2, Transmission 4)
- Denoising
- If rendering the scene: enable OIDN (OpenImageDenoise) in Render and use Normal/Albedo passes for best results.
- If processing an external PNG sequence: Image → Denoise → Composite only; Prefilter=Accurate; HDR only if the images load as float.
- Rendering pipeline (to ensure denoise sticks)
- Output Properties → Post Processing: enable Compositor; disable Sequencer unless you’re using it.
- Prefer rendering to PNG sequence first, then encode to MP4.
These get you the biggest visual gain per millisecond at 32 spp. If you still see sparkle/fireflies on the trims, bump only Clamp Indirect slightly or increase Filter Glossy before raising samples.
---
_**User (2025-10-30 06:38Z)**_
if I send this to flamenco, will it try to send the entire 600gb image sequence?
---
_**Assistant (default)**_
<think><details><summary>Thought Process</summary>**Exploring Flamenco usage**
I need to clarify how Flamenco handles sending a 600GB image sequence. Flamenco, which I think is Blender's render manager, typically sends .blend files and required assets. It can upload dependencies for external sequences unless I'm using shared storage. There are modes like uploaded storage through Flamenco Manager and shared network paths. Best practices suggest using shared storage, referencing images via shared UNC paths, and possibly disabling uploads. I should also look into Flamenco’s integration with Blender Cloud.
**Managing image sequence uploads**
I need to think about how image sequences are handled in terms of uploads. If the sequence is packed or set to "Embed," it can increase size, which isn't ideal. If "Auto pack" is off and absolute paths are used, uploads won’t occur. To ensure smooth operation, it's important to use Shared Storage in the Flamenco config, avoid local paths, and disable "Pack Resources." Also, in Blender, I should turn off "Automatically pack into .blend" to keep things efficient. Keeping images on the network share is a good suggestion too.
**Providing Flamenco configuration steps**
I should check the option for "Include linked libraries," but since the instruction is for minimal verbosity, I’ll keep it concise. We don’t need a status update since we aren’t using tools. To clarify: if configured with shared storage, the answer is no for uploads, yes if in upload mode. I’ll create a checklist including:
- Set Storage Mode to Shared in Flamenco Manager settings.
- Ensure workers have the same mount path and test with a simple job.
- In Blender’s Flamenco add-on, uncheck "Upload job files" and "Include EXR/PNG sequences."
- Avoid packing images and disable automatic packing into .blend.
- Use UNC paths instead of relative paths for consistency.</details></think>
---
Short answer: it depends on your Flamenco setup.
- Shared storage setup: It won’t upload the 600 GB. Workers read the files directly from the shared path.
- Upload/packaging setup: It will try to upload dependencies, which can include your whole sequence.
Do this to avoid any upload:
- Use shared storage in Flamenco Manager.
- Point your Image node to a shared path (UNC like \\server\share\Renders\...); avoid local D:\ paths.
- Ensure workers see the exact same path/mount.
- In Blender: don’t pack external data; disable “Automatically Pack Into .blend”.
- In the Flamenco Blender add‑on: use “shared storage” and disable any “upload job files/dependencies” option.
- Keep linked libraries/textures as external paths on the share.
Quick sanity check: submit a tiny test job and watch the job details—transfer size should be minimal (just the .blend/task files).
---
Reference in New Issue View Git Blame Copy Permalink