Triager-bot/blender-bug-reports
1
0
Code Issues 53 Packages Projects Wiki

Crash when rendering volume #29

New Issue
Open
opened 2026-04-12 17:12:27 +00:00 by Triager-bot · 7 comments
Triager-bot commented 2026-04-12 17:12:27 +00:00
Owner
Copy Link

Original bug report: https://projects.blender.org/blender/blender/issues/157188

System Information
Operating system: Windows-11-10.0.26200-SP0 64 Bits
Graphics card: NVIDIA GeForce RTX 4090/PCIe/SSE2 NVIDIA Corporation 4.6.0 NVIDIA 595.97 Opengl Backend

Blender Version
Broken: version: 5.1.0, branch: blender-v5.1-release, commit date: 2026-03-16 18:50, hash: adfe2921d5f3

Short description of error
As soon as I make my geometry node based volume visible, while rendering with Cycles, Blender will crash.

Exact steps for others to reproduce the error

  1. opened the attached .blend file
  2. switch the viewport shading of the left right viewport to "Rendered"
  3. wait for a few seconds -> crash
Original bug report: https://projects.blender.org/blender/blender/issues/157188 **System Information** Operating system: Windows-11-10.0.26200-SP0 64 Bits Graphics card: NVIDIA GeForce RTX 4090/PCIe/SSE2 NVIDIA Corporation 4.6.0 NVIDIA 595.97 Opengl Backend **Blender Version** Broken: version: 5.1.0, branch: blender-v5.1-release, commit date: 2026-03-16 18:50, hash: `adfe2921d5f3` **Short description of error** As soon as I make my geometry node based volume visible, while rendering with Cycles, Blender will crash. **Exact steps for others to reproduce the error** 1. opened the attached .blend file 2. switch the viewport shading of the left right viewport to "Rendered" 3. wait for a few seconds -> crash
clouds_test.zip
176 KiB
Triager-bot added the
Status
Needs review
 label 2026-04-12 17:12:27 +00:00
Triager-bot commented 2026-04-12 17:12:38 +00:00
Author
Owner
Copy Link

Report is clear

LLM Reasoning

Got it, let's see. The bug report has a title, system info (but we ignore that), Blender version, short description, and steps to reproduce. The steps are clear: open the blend file, switch viewport shading to Rendered, wait. The error is described as crashing when making geometry node volume visible during Cycles render. So does it clearly describe the issue? Yes, because the steps are there, the error is stated. Even though system info is present, we ignore that. The description of the error and steps are clear enough. So the answer is Yes.

JSON Data

{
"llm_judgement": true,
"processing_time": 7.401681000000001
}

<!-- ID: CLARITY_CHECK --> ### Report is clear <details> <summary>LLM Reasoning</summary> Got it, let's see. The bug report has a title, system info (but we ignore that), Blender version, short description, and steps to reproduce. The steps are clear: open the blend file, switch viewport shading to Rendered, wait. The error is described as crashing when making geometry node volume visible during Cycles render. So does it clearly describe the issue? Yes, because the steps are there, the error is stated. Even though system info is present, we ignore that. The description of the error and steps are clear enough. So the answer is Yes. </details> <details> <summary>JSON Data</summary> { "llm_judgement": true, "processing_time": 7.401681000000001 } </details>
👍 1
Triager-bot commented 2026-04-12 17:13:06 +00:00
Author
Owner
Copy Link

Report is specific

LLM Reasoning

Got it, let's analyze this bug report. The title is "Crash when rendering volume". The body says that when making geometry node based volume visible and rendering with Cycles, Blender crashes. The steps are specific: open the attached .blend file, switch viewport shading to Rendered, wait a few seconds, crash.

Wait, but the key here is whether it's specific or generic. The example for specific is "Crashing while using a specific feature while rendering" (like geometry node based volume). The generic example is "Crashing while rendering". Here, the issue is tied to a specific setup: geometry node based volume visible during Cycles render. So that's a specific issue because it's about a particular scenario (geometry node volume + Cycles render) rather than just any rendering crash.

Wait, but let me check again. The user says "As soon as I make my geometry node based volume visible, while rendering with Cycles, Blender will crash." That's a specific condition: geometry node based volume, Cycles render. So it's not a generic "crashing while rendering" but a specific case. So the answer should be Specific? Wait, no, wait the example for specific is "Crashing while using a specific feature while rendering"—yes, that's exactly this. The bug report is about crashing when using a specific feature (geometry node based volume) during rendering. So it's specific. But wait, let me make sure. The steps are to open an attached .blend file, which implies a specific setup. So yes, specific. Wait but the initial thought was maybe generic, but no—because it's about a specific feature (geometry node volume) and a specific action (making it visible during Cycles render). So the answer is Specific? Wait, but let me check the definitions again. The user says: "Specific bug reports are about a specific issue. For example: Crashing while using a specific feature while rendering." That's exactly this case. So yes, Specific. But wait, maybe I'm overcomplicating. Let's see: the bug is when rendering volume (specific type: geometry node based) with Cycles. So it's specific. Therefore, the answer is Specific? Wait no, wait the example for generic is "Crashing while rendering"—which is vague. This one is about crashing when using a specific feature (geometry node volume) during rendering. So that's specific. So the answer should be Specific. But wait, let me check again. The bug report says "As soon as I make my geometry node based volume visible, while rendering with Cycles, Blender will crash." That's a specific scenario. So yes, Specific.

JSON Data

{
"llm_judgement": true,
"processing_time": 27.804476
}

<!-- ID: SPECIFIC_REPORT --> ### Report is specific <details> <summary>LLM Reasoning</summary> Got it, let's analyze this bug report. The title is "Crash when rendering volume". The body says that when making geometry node based volume visible and rendering with Cycles, Blender crashes. The steps are specific: open the attached .blend file, switch viewport shading to Rendered, wait a few seconds, crash. Wait, but the key here is whether it's specific or generic. The example for specific is "Crashing while using a specific feature while rendering" (like geometry node based volume). The generic example is "Crashing while rendering". Here, the issue is tied to a specific setup: geometry node based volume visible during Cycles render. So that's a specific issue because it's about a particular scenario (geometry node volume + Cycles render) rather than just any rendering crash. Wait, but let me check again. The user says "As soon as I make my geometry node based volume visible, while rendering with Cycles, Blender will crash." That's a specific condition: geometry node based volume, Cycles render. So it's not a generic "crashing while rendering" but a specific case. So the answer should be Specific? Wait, no, wait the example for specific is "Crashing while using a specific feature while rendering"—yes, that's exactly this. The bug report is about crashing when using a specific feature (geometry node based volume) during rendering. So it's specific. But wait, let me make sure. The steps are to open an attached .blend file, which implies a specific setup. So yes, specific. Wait but the initial thought was maybe generic, but no—because it's about a specific feature (geometry node volume) and a specific action (making it visible during Cycles render). So the answer is Specific? Wait, but let me check the definitions again. The user says: "Specific bug reports are about a specific issue. For example: Crashing while using a specific feature while rendering." That's exactly this case. So yes, Specific. But wait, maybe I'm overcomplicating. Let's see: the bug is when rendering volume (specific type: geometry node based) with Cycles. So it's specific. Therefore, the answer is Specific? Wait no, wait the example for generic is "Crashing while rendering"—which is vague. This one is about crashing when using a specific feature (geometry node volume) during rendering. So that's specific. So the answer should be Specific. But wait, let me check again. The bug report says "As soon as I make my geometry node based volume visible, while rendering with Cycles, Blender will crash." That's a specific scenario. So yes, Specific. </details> <details> <summary>JSON Data</summary> { "llm_judgement": true, "processing_time": 27.804476 } </details>
👍 1
Triager-bot commented 2026-04-12 17:13:57 +00:00
Author
Owner
Copy Link

Report flagged as duplicate by LLM

Cycles: Crash on instanced volume grids from geometry nodes

https://projects.blender.org/blender/blender/issues/140364

System Information
Operating system: Windows-10-10.0.19045-SP0 64 Bits
Graphics card: NVIDIA GeForce GTX 1060 6GB/PCIe/SSE2 NVIDIA Corporation 4.6.0 NVIDIA 572.16 Opengl Backend

Blender Version
Broken: version: 5.0.0 Alpha, branch: main, commit date: 2025-06-10 10:37, hash: 368a64f3869d
Worked: (newest version of Blender that worked as expected)

Short description of error
Its crash on if you have enabled CUDA GPU acceleration in attached example project on attempt to start viewport render.

Exact steps for others to reproduce the error

  1. Open example file.
  2. Make sure you have cycles with enabled CUDA.
  3. Try to render (you can do even on CPU).
    (you may try to tag geometry nodes 3-6 times to make sure crash is there)
LLM Reasoning

Got it, let's analyze the two bug reports. First, look at the descriptions and steps.

Bug report 1: Crash when rendering volume with geometry node based volume visible in Cycles. Steps involve opening a .blend, switching viewport to Rendered, waiting for crash.

Bug report 2: Crash on instanced volume grids from geometry nodes when using CUDA GPU acceleration (or even CPU) in Cycles. Steps are open example file, enable cycles with CUDA, try to render (tag geometry nodes multiple times).

The key points: Both involve crashes related to geometry node volumes in Cycles. But the first is about rendering (viewport shading to Rendered), the second is about starting viewport render or using CUDA. Wait, but both mention geometry node volumes and Cycles. However, the steps differ a bit—first is switching viewport shading, second is enabling CUDA and trying to render. Also, the hardware (RTX 4090 vs GTX 1060) and Blender versions (5.1.0 vs 5.0.0 Alpha) are different, but the core issue might be similar. But do they describe the same problem? Let's check the descriptions: both mention crashes with geometry node volumes in Cycles. The first is when making volume visible (viewport shading), the second is on render attempt with CUDA. Are these the same underlying issue? Maybe, but let's see if the steps are similar enough. Wait, the question is whether they are duplicates based on description and steps. Let's compare:

Bug 1: Steps are open .blend, switch viewport to Rendered, wait → crash.

Bug 2: Steps are open example file, enable cycles with CUDA, try to render (tag geometry nodes) → crash.

The common elements: geometry node volumes, Cycles rendering, crash. But the triggers differ (viewport shading vs render attempt). However, maybe they are the same issue but different reproduction steps. But the question is if they are duplicates. Let's think—do both reports describe the same problem? The first is about volume visibility in viewport leading to crash, the second is about instanced volume grids from geometry nodes causing crash on render (with CUDA). Are these the same? Maybe not exactly, but let's check the descriptions again.

Wait, the user says to focus on 'Description of issue' and 'Steps to reproduce'. Let's list them:

Bug 1 Description: Crash when rendering volume (geometry node based) visible in Cycles. Steps: open .blend, switch viewport shading to Rendered, wait → crash.

Bug 2 Description: Crash on instanced volume grids from geometry nodes when using CUDA GPU acceleration (or CPU) in Cycles. Steps: open example file, enable cycles with CUDA, try to render (tag geometry nodes) → crash.

The core issue is crashes related to geometry node volumes in Cycles. But the steps are different. However, maybe they are duplicates because both involve geometry node volumes and Cycles crashes. But let's see if the problem is the same. Alternatively, maybe not. Wait, the first report's crash happens when making volume visible (viewport shading), the second when trying to render (with CUDA). Are these two different scenarios of the same underlying bug? Possibly. But the question is whether they are duplicates. Let's check the titles: "Crash when rendering volume" vs "Cycles: Crash on instanced volume grids from geometry nodes". The titles suggest similar issues. The descriptions both mention crashes with geometry node volumes in Cycles. So maybe yes, they are duplicates. Wait, but let's confirm.

Alternatively, maybe not. Let's think again. The first report's steps involve viewport shading (Rendered) leading to crash, the second involves render attempt (with CUDA). But both are related to rendering volume from geometry nodes. So perhaps they are the same issue. Therefore, the answer is Yes? Wait, but let's check the details. The first report's system has RTX 4090, the second GTX 1060. Blender versions differ (5.1.0 vs 5.0.0 Alpha). But duplicates can be across different systems and versions if the issue is the same. So based on the descriptions and steps, they seem to describe the same problem: crashes with geometry node volumes in Cycles. Therefore, the answer is Yes? Wait, but maybe I'm wrong. Let me recheck.

Wait, the first report's crash happens when switching viewport shading to Rendered (so viewport rendering), the second when trying to render (maybe a full render or viewport render). Both involve Cycles and geometry node volumes. So yes, they are duplicates. Therefore, the answer is Yes.

JSON Data

{
"llm_judgement": true,
"processing_time": 49.643907,
"duplicate_report_number": "140364"
}

<!-- ID: CHECK_DUPLICATE --> ### Report flagged as duplicate by LLM <details> <summary>Cycles: Crash on instanced volume grids from geometry nodes</summary> https://projects.blender.org/blender/blender/issues/140364 **System Information** Operating system: Windows-10-10.0.19045-SP0 64 Bits Graphics card: NVIDIA GeForce GTX 1060 6GB/PCIe/SSE2 NVIDIA Corporation 4.6.0 NVIDIA 572.16 Opengl Backend **Blender Version** Broken: version: 5.0.0 Alpha, branch: main, commit date: 2025-06-10 10:37, hash: `368a64f3869d` Worked: (newest version of Blender that worked as expected) **Short description of error** Its crash on if you have enabled CUDA GPU acceleration in attached example project on attempt to start viewport render. **Exact steps for others to reproduce the error** 1. Open example file. 2. Make sure you have cycles with enabled CUDA. 3. Try to render (you can do even on CPU). (you may try to tag geometry nodes 3-6 times to make sure crash is there) </details> <details> <summary>LLM Reasoning</summary> Got it, let's analyze the two bug reports. First, look at the descriptions and steps. Bug report 1: Crash when rendering volume with geometry node based volume visible in Cycles. Steps involve opening a .blend, switching viewport to Rendered, waiting for crash. Bug report 2: Crash on instanced volume grids from geometry nodes when using CUDA GPU acceleration (or even CPU) in Cycles. Steps are open example file, enable cycles with CUDA, try to render (tag geometry nodes multiple times). The key points: Both involve crashes related to geometry node volumes in Cycles. But the first is about rendering (viewport shading to Rendered), the second is about starting viewport render or using CUDA. Wait, but both mention geometry node volumes and Cycles. However, the steps differ a bit—first is switching viewport shading, second is enabling CUDA and trying to render. Also, the hardware (RTX 4090 vs GTX 1060) and Blender versions (5.1.0 vs 5.0.0 Alpha) are different, but the core issue might be similar. But do they describe the same problem? Let's check the descriptions: both mention crashes with geometry node volumes in Cycles. The first is when making volume visible (viewport shading), the second is on render attempt with CUDA. Are these the same underlying issue? Maybe, but let's see if the steps are similar enough. Wait, the question is whether they are duplicates based on description and steps. Let's compare: Bug 1: Steps are open .blend, switch viewport to Rendered, wait → crash. Bug 2: Steps are open example file, enable cycles with CUDA, try to render (tag geometry nodes) → crash. The common elements: geometry node volumes, Cycles rendering, crash. But the triggers differ (viewport shading vs render attempt). However, maybe they are the same issue but different reproduction steps. But the question is if they are duplicates. Let's think—do both reports describe the same problem? The first is about volume visibility in viewport leading to crash, the second is about instanced volume grids from geometry nodes causing crash on render (with CUDA). Are these the same? Maybe not exactly, but let's check the descriptions again. Wait, the user says to focus on 'Description of issue' and 'Steps to reproduce'. Let's list them: Bug 1 Description: Crash when rendering volume (geometry node based) visible in Cycles. Steps: open .blend, switch viewport shading to Rendered, wait → crash. Bug 2 Description: Crash on instanced volume grids from geometry nodes when using CUDA GPU acceleration (or CPU) in Cycles. Steps: open example file, enable cycles with CUDA, try to render (tag geometry nodes) → crash. The core issue is crashes related to geometry node volumes in Cycles. But the steps are different. However, maybe they are duplicates because both involve geometry node volumes and Cycles crashes. But let's see if the problem is the same. Alternatively, maybe not. Wait, the first report's crash happens when making volume visible (viewport shading), the second when trying to render (with CUDA). Are these two different scenarios of the same underlying bug? Possibly. But the question is whether they are duplicates. Let's check the titles: "Crash when rendering volume" vs "Cycles: Crash on instanced volume grids from geometry nodes". The titles suggest similar issues. The descriptions both mention crashes with geometry node volumes in Cycles. So maybe yes, they are duplicates. Wait, but let's confirm. Alternatively, maybe not. Let's think again. The first report's steps involve viewport shading (Rendered) leading to crash, the second involves render attempt (with CUDA). But both are related to rendering volume from geometry nodes. So perhaps they are the same issue. Therefore, the answer is Yes? Wait, but let's check the details. The first report's system has RTX 4090, the second GTX 1060. Blender versions differ (5.1.0 vs 5.0.0 Alpha). But duplicates can be across different systems and versions if the issue is the same. So based on the descriptions and steps, they seem to describe the same problem: crashes with geometry node volumes in Cycles. Therefore, the answer is Yes? Wait, but maybe I'm wrong. Let me recheck. Wait, the first report's crash happens when switching viewport shading to Rendered (so viewport rendering), the second when trying to render (maybe a full render or viewport render). Both involve Cycles and geometry node volumes. So yes, they are duplicates. Therefore, the answer is Yes. </details> <details> <summary>JSON Data</summary> { "llm_judgement": true, "processing_time": 49.643907, "duplicate_report_number": "140364" } </details>
👎 1
Triager-bot commented 2026-04-12 17:14:09 +00:00
Author
Owner
Copy Link

Report flagged as NOT a duplicate by LLM

Volume emission shader crashing blender

https://projects.blender.org/blender/blender/issues/154772

System Information
Operating system: Windows-10-10.0.19045-SP0 64 Bits
Graphics card: NVIDIA GeForce GTX 970/PCIe/SSE2 NVIDIA Corporation 4.6.0 NVIDIA 581.80 Opengl Backend

Blender Version
Broken: version: 5.0.1, branch: blender-v5.0-release, commit date: 2025-12-15 16:36, hash: a3db93c5b259
Worked: (newest version of Blender that worked as expected)

Short description of error
I was using volumetric emission shader with noise node, I'm unsure what caused the crash but it seems to happen somewhat consistently.

Exact steps for others to reproduce the error
Create a volumetric emission shader and attach any generated 3d noise to replicate the bug.

LLM Reasoning

Got it, let's analyze these two bug reports. First, look at the description and steps.

Bug report 1: Crash when rendering volume, using geometry node based volume, Cycles render. Steps involve opening a .blend, switching viewport to Rendered, waiting for crash.

Bug report 2: Volume emission shader with noise node causing crash. Steps are creating volumetric emission shader with 3d noise.

The key here is the cause and steps. Report 1 mentions geometry node based volume and Cycles render, while report 2 is about volumetric emission shader with noise. Are these the same? The descriptions are different: one is geometry node volume, the other is volume emission shader with noise. So they might be different issues. Since the focus is on description and steps, and they don't match exactly, the answer should be No.

JSON Data

{
"llm_judgement": false,
"processing_time": 10.852578,
"duplicate_report_number": "154772"
}

<!-- ID: CHECK_DUPLICATE --> ### Report flagged as NOT a duplicate by LLM <details> <summary>Volume emission shader crashing blender</summary> https://projects.blender.org/blender/blender/issues/154772 **System Information** Operating system: Windows-10-10.0.19045-SP0 64 Bits Graphics card: NVIDIA GeForce GTX 970/PCIe/SSE2 NVIDIA Corporation 4.6.0 NVIDIA 581.80 Opengl Backend **Blender Version** Broken: version: 5.0.1, branch: blender-v5.0-release, commit date: 2025-12-15 16:36, hash: `a3db93c5b259` Worked: (newest version of Blender that worked as expected) **Short description of error** I was using volumetric emission shader with noise node, I'm unsure what caused the crash but it seems to happen somewhat consistently. **Exact steps for others to reproduce the error** Create a volumetric emission shader and attach any generated 3d noise to replicate the bug. </details> <details> <summary>LLM Reasoning</summary> Got it, let's analyze these two bug reports. First, look at the description and steps. Bug report 1: Crash when rendering volume, using geometry node based volume, Cycles render. Steps involve opening a .blend, switching viewport to Rendered, waiting for crash. Bug report 2: Volume emission shader with noise node causing crash. Steps are creating volumetric emission shader with 3d noise. The key here is the cause and steps. Report 1 mentions geometry node based volume and Cycles render, while report 2 is about volumetric emission shader with noise. Are these the same? The descriptions are different: one is geometry node volume, the other is volume emission shader with noise. So they might be different issues. Since the focus is on description and steps, and they don't match exactly, the answer should be No. </details> <details> <summary>JSON Data</summary> { "llm_judgement": false, "processing_time": 10.852578, "duplicate_report_number": "154772" } </details>
👍 1
Triager-bot commented 2026-04-12 17:14:29 +00:00
Author
Owner
Copy Link

Report flagged as NOT a duplicate by LLM

Geometry Nodes / Eevee - crash when rendering points with volume shader and no geometry

https://projects.blender.org/blender/blender/issues/138159

System Information
Operating system: Windows-10-10.0.19045-SP0 64 Bits
Graphics card: NVIDIA Corporation NVIDIA GeForce RTX 3080 Ti NVIDIA 576.02

Blender Version
Broken: version: 4.5.0 Alpha, Commit date: 2025-04-28 18:16, hash: 2f96afb4be4f
broken: 4.4.1

Exact steps for others to reproduce the error
The attached file has geometry nodes with points on surface. Switch to rendered mode in viewport. It should crash Blender.

LLM Reasoning

Got it, let's analyze these two bug reports. First, look at the description and steps.

Bug Report 1: Crash when rendering volume (Cycles) with geometry node based volume visible. Steps involve opening a .blend, switching viewport to Rendered, waiting for crash.

Bug Report 2: Geometry Nodes / Eevee - crash when rendering points with volume shader and no geometry. Steps: attached file has geometry nodes with points on surface, switch to rendered mode, crash.

Wait, the first uses Cycles, the second mentions Eevee (but maybe that's a typo? Or different render engine). Also, the first is about "volume" visibility in geometry node based volume, the second is about points with volume shader and no geometry. The steps are similar (switch to rendered viewport), but the context differs: one is Cycles, the other mentions Eevee (maybe a mistake, but the core issue might be different). Also, the first's error is when making volume visible in Cycles, the second is points with volume shader and no geometry. Are these the same? Let's check the key elements:

  • Both involve rendering with some volume-related setup.
  • But Report 1 is Cycles, Report 2 mentions Eevee (maybe a different engine). Also, Report 1's issue is "geometry node based volume visible" leading to crash in Cycles. Report 2 is "points on surface with volume shader and no geometry" leading to crash (maybe Eevee or another engine). The steps are similar (switch to rendered viewport), but the underlying setup (volume vs points with volume shader) might be different. Also, the render engines differ (Cycles vs possibly Eevee). So they might not be the same issue. Therefore, the answer is No.
JSON Data

{
"llm_judgement": false,
"processing_time": 19.925149,
"duplicate_report_number": "138159"
}

<!-- ID: CHECK_DUPLICATE --> ### Report flagged as NOT a duplicate by LLM <details> <summary>Geometry Nodes / Eevee - crash when rendering points with volume shader and no geometry</summary> https://projects.blender.org/blender/blender/issues/138159 **System Information** Operating system: Windows-10-10.0.19045-SP0 64 Bits Graphics card: NVIDIA Corporation NVIDIA GeForce RTX 3080 Ti NVIDIA 576.02 **Blender Version** Broken: version: 4.5.0 Alpha, Commit date: 2025-04-28 18:16, hash: `2f96afb4be4f` broken: 4.4.1 **Exact steps for others to reproduce the error** The attached file has geometry nodes with points on surface. Switch to rendered mode in viewport. It should crash Blender. </details> <details> <summary>LLM Reasoning</summary> Got it, let's analyze these two bug reports. First, look at the description and steps. Bug Report 1: Crash when rendering volume (Cycles) with geometry node based volume visible. Steps involve opening a .blend, switching viewport to Rendered, waiting for crash. Bug Report 2: Geometry Nodes / Eevee - crash when rendering points with volume shader and no geometry. Steps: attached file has geometry nodes with points on surface, switch to rendered mode, crash. Wait, the first uses Cycles, the second mentions Eevee (but maybe that's a typo? Or different render engine). Also, the first is about "volume" visibility in geometry node based volume, the second is about points with volume shader and no geometry. The steps are similar (switch to rendered viewport), but the context differs: one is Cycles, the other mentions Eevee (maybe a mistake, but the core issue might be different). Also, the first's error is when making volume visible in Cycles, the second is points with volume shader and no geometry. Are these the same? Let's check the key elements: - Both involve rendering with some volume-related setup. - But Report 1 is Cycles, Report 2 mentions Eevee (maybe a different engine). Also, Report 1's issue is "geometry node based volume visible" leading to crash in Cycles. Report 2 is "points on surface with volume shader and no geometry" leading to crash (maybe Eevee or another engine). The steps are similar (switch to rendered viewport), but the underlying setup (volume vs points with volume shader) might be different. Also, the render engines differ (Cycles vs possibly Eevee). So they might not be the same issue. Therefore, the answer is No. </details> <details> <summary>JSON Data</summary> { "llm_judgement": false, "processing_time": 19.925149, "duplicate_report_number": "138159" } </details>
👍 1
Triager-bot commented 2026-04-12 17:14:43 +00:00
Author
Owner
Copy Link

Report flagged as NOT a duplicate by LLM

A volume shader on a point cloud in EEVEE crashes Blender

https://projects.blender.org/blender/blender/issues/152669

System Information
Operating system: Windows-11-10.0.26100-SP0 64 Bits
Graphics card: NVIDIA GeForce RTX 3050/PCIe/SSE2 NVIDIA Corporation 4.6.0 NVIDIA 591.74 Opengl Backend

Blender Version
Broken: version: 5.1.0 Alpha, branch: main, commit date: 2026-01-02 21:29, hash: 7178bae1d1be
Broken: 5.0
Broken: 4.4
Worked: 4.5.5
Worked: 4.3 (doesn't crash, but turns everything black)

Short description of error
Adding a volume shader to a point cloud in EEVEE will crash Blender

Exact steps for others to reproduce the error

Note: support was supposed to be added in https://projects.blender.org/blender/blender/pulls/142095

LLM Reasoning

Got it, let's analyze the two bug reports. First, look at the descriptions and steps.

Bug Report 1: Crash when rendering volume with geometry node based volume in Cycles. Steps involve opening a .blend, switching viewport to Rendered, waiting for crash.

Bug Report 2: Volume shader on point cloud in EEVEE crashes Blender. Steps: add point cloud, add volume shader, go to rendered view, wait for crash.

The key differences:

  • Renderer: Cycles vs EEVEE (different render engines)
  • Object type: geometry node based volume vs point cloud
  • The first is about a specific volume from geometry nodes in Cycles, the second is a point cloud with volume shader in EEVEE.

Since the render engine and object types are different, they're not the same issue. So the answer is No.

JSON Data

{
"llm_judgement": false,
"processing_time": 12.653649000000001,
"duplicate_report_number": "152669"
}

<!-- ID: CHECK_DUPLICATE --> ### Report flagged as NOT a duplicate by LLM <details> <summary>A volume shader on a point cloud in EEVEE crashes Blender</summary> https://projects.blender.org/blender/blender/issues/152669 **System Information** Operating system: Windows-11-10.0.26100-SP0 64 Bits Graphics card: NVIDIA GeForce RTX 3050/PCIe/SSE2 NVIDIA Corporation 4.6.0 NVIDIA 591.74 Opengl Backend **Blender Version** Broken: version: 5.1.0 Alpha, branch: main, commit date: 2026-01-02 21:29, hash: `7178bae1d1be` Broken: 5.0 Broken: 4.4 Worked: 4.5.5 Worked: 4.3 (doesn't crash, but turns everything black) **Short description of error** Adding a volume shader to a point cloud in EEVEE will crash Blender **Exact steps for others to reproduce the error** - Open Blender and add a point cloud - In the material tab, remove the principled BSDF and add a volume shader - Here's a file setup to this point [152669 - Point cloud volume scatter crashes Blender.blend](/attachments/1015aa7a-2f63-4b11-8784-28a79ade1f8e) - Go into rendered view and wait for Blender to crash Note: support was supposed to be added in https://projects.blender.org/blender/blender/pulls/142095 </details> <details> <summary>LLM Reasoning</summary> Got it, let's analyze the two bug reports. First, look at the descriptions and steps. Bug Report 1: Crash when rendering volume with geometry node based volume in Cycles. Steps involve opening a .blend, switching viewport to Rendered, waiting for crash. Bug Report 2: Volume shader on point cloud in EEVEE crashes Blender. Steps: add point cloud, add volume shader, go to rendered view, wait for crash. The key differences: - Renderer: Cycles vs EEVEE (different render engines) - Object type: geometry node based volume vs point cloud - The first is about a specific volume from geometry nodes in Cycles, the second is a point cloud with volume shader in EEVEE. Since the render engine and object types are different, they're not the same issue. So the answer is No. </details> <details> <summary>JSON Data</summary> { "llm_judgement": false, "processing_time": 12.653649000000001, "duplicate_report_number": "152669" } </details>
👍 1
Triager-bot commented 2026-04-12 17:15:07 +00:00
Author
Owner
Copy Link

Report flagged as NOT a duplicate by LLM

Crash when rendering specific object in Cycles (viewport and final render)

https://projects.blender.org/blender/blender/issues/155897

System Information
Operating system: Windows-11-10.0.26200-SP0 64 Bits
Graphics card: NVIDIA GeForce RTX 3060 Ti NVIDIA Corporation NVIDIA 595.79 Vulkan Backend

Blender Version
Broken: version: 5.1.0, branch: blender-v5.1-release, commit date: 2026-03-16 18:50, hash: adfe2921d5f3
Worked: (newest version of Blender that worked as expected)

Short description of error
Blender crashes instantly when attempting to render a specific object in Cycles. The issue persists even when the object is isolated in a separate scene/file.

Exact steps for others to reproduce the error
Open the provided .blend file

Switch to Viewport Shading: Rendered
OR
Press F12

Observe immediate crash

LLM Reasoning

Got it, let's analyze these two bug reports. First, look at the key sections: description and steps.

Bug report 1: Crash when rendering volume (geometry node based) in Cycles viewport. Steps involve opening a .blend, switching to Rendered viewport, waiting for crash.

Bug report 2: Crash when rendering specific object in Cycles (viewport or final render). Steps are open .blend, switch to Rendered or press F12, immediate crash.

The core issue here is both are crashes during rendering in Cycles. But the first mentions a volume from geometry nodes, the second a "specific object" without specifying type. However, the steps are similar (opening file, switching to rendered viewport). Wait, but the first says "wait for a few seconds", the second says "immediate crash". Also, the first is about volume, the second about a specific object. Are they the same? Let's check if the context matches.

Wait, the question is whether they are the same issue. The descriptions: one is volume (geometry node based), the other is a specific object. But maybe the "specific object" in report 2 could be that volume? But the steps for report 1 involve waiting, report 2 immediate. Also, different graphics cards (RTX 4090 vs 3060 Ti) but same Blender version. Hmm.

But the key is: are the issues duplicates? Let's see. The first is about rendering a volume (geometry node based) in viewport leading to crash after waiting. The second is about rendering a specific object (could be any, maybe the same volume?) leading to immediate crash. But the steps differ slightly (wait vs immediate). Also, the titles are different: one is "Crash when rendering volume", the other "Crash when rendering specific object". So they might not be the same. Wait, but maybe the "specific object" in report 2 is that volume? But the steps for report 1 have a wait time, report 2 immediate. Also, different backends (OpenGL vs Vulkan). So probably not the same issue. Therefore, answer is No.

JSON Data

{
"llm_judgement": false,
"processing_time": 23.659752,
"duplicate_report_number": "155897"
}

<!-- ID: CHECK_DUPLICATE --> ### Report flagged as NOT a duplicate by LLM <details> <summary>Crash when rendering specific object in Cycles (viewport and final render)</summary> https://projects.blender.org/blender/blender/issues/155897 **System Information** Operating system: Windows-11-10.0.26200-SP0 64 Bits Graphics card: NVIDIA GeForce RTX 3060 Ti NVIDIA Corporation NVIDIA 595.79 Vulkan Backend **Blender Version** Broken: version: 5.1.0, branch: blender-v5.1-release, commit date: 2026-03-16 18:50, hash: `adfe2921d5f3` Worked: (newest version of Blender that worked as expected) **Short description of error** Blender crashes instantly when attempting to render a specific object in Cycles. The issue persists even when the object is isolated in a separate scene/file. **Exact steps for others to reproduce the error** Open the provided .blend file Switch to Viewport Shading: Rendered OR Press F12 Observe immediate crash </details> <details> <summary>LLM Reasoning</summary> Got it, let's analyze these two bug reports. First, look at the key sections: description and steps. Bug report 1: Crash when rendering volume (geometry node based) in Cycles viewport. Steps involve opening a .blend, switching to Rendered viewport, waiting for crash. Bug report 2: Crash when rendering specific object in Cycles (viewport or final render). Steps are open .blend, switch to Rendered or press F12, immediate crash. The core issue here is both are crashes during rendering in Cycles. But the first mentions a volume from geometry nodes, the second a "specific object" without specifying type. However, the steps are similar (opening file, switching to rendered viewport). Wait, but the first says "wait for a few seconds", the second says "immediate crash". Also, the first is about volume, the second about a specific object. Are they the same? Let's check if the context matches. Wait, the question is whether they are the same issue. The descriptions: one is volume (geometry node based), the other is a specific object. But maybe the "specific object" in report 2 could be that volume? But the steps for report 1 involve waiting, report 2 immediate. Also, different graphics cards (RTX 4090 vs 3060 Ti) but same Blender version. Hmm. But the key is: are the issues duplicates? Let's see. The first is about rendering a volume (geometry node based) in viewport leading to crash after waiting. The second is about rendering a specific object (could be any, maybe the same volume?) leading to immediate crash. But the steps differ slightly (wait vs immediate). Also, the titles are different: one is "Crash when rendering volume", the other "Crash when rendering specific object". So they might not be the same. Wait, but maybe the "specific object" in report 2 is that volume? But the steps for report 1 have a wait time, report 2 immediate. Also, different backends (OpenGL vs Vulkan). So probably not the same issue. Therefore, answer is No. </details> <details> <summary>JSON Data</summary> { "llm_judgement": false, "processing_time": 23.659752, "duplicate_report_number": "155897" } </details>
👍 1
Triager-bot added Trager-Bot Will Send Comment
Status
Bad Judgement
 and removed
Status
Needs review
 labels 2026-04-12 17:15:57 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Status
Bad Judgement
Status
Good judgement
Status
Needs review
Status
Uncertain Judgement
Trager-Bot Will Send Comment
No Label
Status
Bad Judgement
 Trager-Bot Will Send Comment
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
Triager-bot
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Triager-bot/blender-bug-reports#29
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?