遮罩重绘出现问题。

[huongphams86jz8-stack]

Custom Node Testing

• I have tried disabling custom nodes and the issue persists (see how to disable custom nodes if you need help)

Expected Behavior

lanpaint节点或是其他任何重绘的遮罩局部修改节点都出图变成色块。

Actual Behavior

[INFO] To see the GUI go to: http://127.0.0.1:8188
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[]
[]
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[INFO] got prompt

😺dzNodes: LayerStyle -> ImageScaleByAspectRatio V2 Processed 1 image(s).

Expanding/Contracting Mask: 100%|████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 8.97it/s]
[INFO] Using xformers attention in VAE
[INFO] Using xformers attention in VAE
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[INFO] gguf qtypes: F32 (145), Q8_0 (253)
[WARNING] Dequantizing token_embd.weight to prevent runtime OOM.
[INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] Requested to load ZImageTEModel_
[INFO] loaded completely; 9554.67 MB usable, 4424.19 MB loaded, full load: True
[INFO] Requested to load AutoencodingEngine
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 91 KB.
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 91 KB.
[INFO] Found quantization metadata version 1
[INFO] Detected mixed precision quantization
[INFO] Using mixed precision operations
[INFO] Native ops: float8_e4m3fn, float8_e5m2, nvfp4, mxfp8, int8_tensorwise, convrot_w4a4
[INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16
[INFO] model_type FLOW
[rgthree-comfy][Seed] Got "-1" as passed seed. This shouldn't happen when queueing from the ComfyUI frontend.
[rgthree-comfy][Seed] Server-generated random seed 386709062484410 and saving to workflow.
[rgthree-comfy][Seed] NOTE: Re-queues passing in "{seed}" and server-generated random seed won't be cached.
CFGGuider outer_sample
[INFO] Requested to load Lumina2
[INFO] Unloaded partially: 1108.40 MB freed, 3315.78 MB remains loaded, 176.64 MB buffer reserved, lowvram patches: 0
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 4552MB Staged. 0 patches attached. Force pre-loaded 205 weights: 1045 KB.
output shape torch.Size([1, 16, 128, 128])
input mask torch.Size([1, 16, 128, 128]) <class 'torch.Tensor'> tensor(1., device='cuda:0') tensor(0., device='cuda:0')
target output_shape torch.Size([1, 16, 128, 128])
input_mask.ndim: 4 output_shape len: 4
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:27<00:00, 3.03s/it]
[INFO] Unloaded partially: 3315.78 MB freed, 0.00 MB remains loaded, 2276.09 MB buffer reserved, lowvram patches: 0
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 91 KB.

😺dzNodes: LayerStyle -> ImageReelComposit Processed 1 image(s).

comfyui lumi batcher overwrite task done
[INFO] Prompt executed in 45.31 seconds
[INFO] got prompt
[rgthree-comfy][Seed] Got "-1" as passed seed. This shouldn't happen when queueing from the ComfyUI frontend.
[rgthree-comfy][Seed] Server-generated random seed 440163976717680 and saving to workflow.
[rgthree-comfy][Seed] NOTE: Re-queues passing in "{seed}" and server-generated random seed won't be cached.
CFGGuider outer_sample
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 4552MB Staged. 0 patches attached. Force pre-loaded 205 weights: 1045 KB.
output shape torch.Size([1, 16, 128, 128])
input mask torch.Size([1, 16, 128, 128]) <class 'torch.Tensor'> tensor(1., device='cuda:0') tensor(0., device='cuda:0')
target output_shape torch.Size([1, 16, 128, 128])
input_mask.ndim: 4 output_shape len: 4
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:27<00:00, 3.06s/it]
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 91 KB.

😺dzNodes: LayerStyle -> ImageReelComposit Processed 1 image(s).

comfyui lumi batcher overwrite task done
[INFO] Prompt executed in 29.17 seconds
[INFO] got prompt
[rgthree-comfy][Seed] Got "-1" as passed seed. This shouldn't happen when queueing from the ComfyUI frontend.
[rgthree-comfy][Seed] Server-generated random seed 156819529289517 and saving to workflow.
[rgthree-comfy][Seed] NOTE: Re-queues passing in "{seed}" and server-generated random seed won't be cached.
CFGGuider outer_sample
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 4552MB Staged. 0 patches attached. Force pre-loaded 205 weights: 1045 KB.

Steps to Reproduce

Debug Logs

[INFO] To see the GUI go to: http://127.0.0.1:8188
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[]
[]
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[WARNING] [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[INFO] got prompt
# 😺dzNodes: LayerStyle -> ImageScaleByAspectRatio V2 Processed 1 image(s).
Expanding/Contracting Mask: 100%|████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  8.97it/s]
[INFO] Using xformers attention in VAE
[INFO] Using xformers attention in VAE
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[INFO] gguf qtypes: F32 (145), Q8_0 (253)
[WARNING] Dequantizing token_embd.weight to prevent runtime OOM.
[INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] Requested to load ZImageTEModel_
[INFO] loaded completely; 9554.67 MB usable, 4424.19 MB loaded, full load: True
[INFO] Requested to load AutoencodingEngine
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 91 KB.
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 91 KB.
[INFO] Found quantization metadata version 1
[INFO] Detected mixed precision quantization
[INFO] Using mixed precision operations
[INFO] Native ops: float8_e4m3fn, float8_e5m2, nvfp4, mxfp8, int8_tensorwise, convrot_w4a4
[INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16
[INFO] model_type FLOW
[rgthree-comfy][Seed] Got "-1" as passed seed. This shouldn't happen when queueing from the ComfyUI frontend.
[rgthree-comfy][Seed] Server-generated random seed 386709062484410 and saving to workflow.
[rgthree-comfy][Seed] NOTE: Re-queues passing in "{seed}" and server-generated random seed won't be cached.
CFGGuider outer_sample
[INFO] Requested to load Lumina2
[INFO] Unloaded partially: 1108.40 MB freed, 3315.78 MB remains loaded, 176.64 MB buffer reserved, lowvram patches: 0
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 4552MB Staged. 0 patches attached. Force pre-loaded 205 weights: 1045 KB.
output shape torch.Size([1, 16, 128, 128])
input mask torch.Size([1, 16, 128, 128]) <class 'torch.Tensor'> tensor(1., device='cuda:0') tensor(0., device='cuda:0')
target output_shape torch.Size([1, 16, 128, 128])
input_mask.ndim: 4 output_shape len: 4
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:27<00:00,  3.03s/it]
[INFO] Unloaded partially: 3315.78 MB freed, 0.00 MB remains loaded, 2276.09 MB buffer reserved, lowvram patches: 0
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 91 KB.
# 😺dzNodes: LayerStyle -> ImageReelComposit Processed 1 image(s).
comfyui lumi batcher overwrite task done
[INFO] Prompt executed in 45.31 seconds
[INFO] got prompt
[rgthree-comfy][Seed] Got "-1" as passed seed. This shouldn't happen when queueing from the ComfyUI frontend.
[rgthree-comfy][Seed] Server-generated random seed 440163976717680 and saving to workflow.
[rgthree-comfy][Seed] NOTE: Re-queues passing in "{seed}" and server-generated random seed won't be cached.
CFGGuider outer_sample
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 4552MB Staged. 0 patches attached. Force pre-loaded 205 weights: 1045 KB.
output shape torch.Size([1, 16, 128, 128])
input mask torch.Size([1, 16, 128, 128]) <class 'torch.Tensor'> tensor(1., device='cuda:0') tensor(0., device='cuda:0')
target output_shape torch.Size([1, 16, 128, 128])
input_mask.ndim: 4 output_shape len: 4
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:27<00:00,  3.06s/it]
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 91 KB.
# 😺dzNodes: LayerStyle -> ImageReelComposit Processed 1 image(s).
comfyui lumi batcher overwrite task done
[INFO] Prompt executed in 29.17 seconds
[INFO] got prompt
[rgthree-comfy][Seed] Got "-1" as passed seed. This shouldn't happen when queueing from the ComfyUI frontend.
[rgthree-comfy][Seed] Server-generated random seed 156819529289517 and saving to workflow.
[rgthree-comfy][Seed] NOTE: Re-queues passing in "{seed}" and server-generated random seed won't be cached.
CFGGuider outer_sample
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 4552MB Staged. 0 patches attached. Force pre-loaded 205 weights: 1045 KB.

Other

[coderabbitai]

🔗 Related PRs

#14110 - Add SeedVR2 support (CORE-6) [merged]
#14956 - Add continuous sampler and VAE decode batching [open]
#15020 - Add native Hunyuan3D 2.1 PBR paint (mesh -> multiview -> textured GLB) [open]

---

🧪 Issue enrichment is currently in open beta.

You can configure auto-planning by selecting labels in the issue_enrichment configuration.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord!