CRM failed

[DenisKochetov]

Hi, thanks for another lighning fast implementation. Is 20 gb of vram not enough? EDIT: I checked monitoring, it was actually regular RAM, over 16gb is needed for sure.

To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: /home/ubuntu/ComfyUI/custom_nodes/ComfyUI-Manager/extension-node-map.json
got prompt
[Comfy3D] [WARNING] [Load_CRM_MVDiffusion_Model] can't find checkpoint /home/ubuntu/ComfyUI/custom_nodes/ComfyUI-3D-Pack/checkpoints/crm/ccm-diffusion.pth, will download it from repo Zhengyi/CRM instead
ccm-diffusion.pth: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████| 6.16G/6.16G [00:39<00:00, 155MB/s]
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 5 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 1024 and using 5 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 5 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 1024 and using 5 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 1024 and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 1024 and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 1024 and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 1024 and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 1024 and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 1024 and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 1024 and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 1024 and using 20 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 1024 and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 1024 and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 1024 and using 10 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 5 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 1024 and using 5 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 5 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 1024 and using 5 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 5 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 1024 and using 5 heads.
Loaded ViT-H-14 model config.
Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k).
making attention of type 'vanilla-xformers' with 512 in_channels
building MemoryEfficientAttnBlock with 512 in_channels...
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla-xformers' with 512 in_channels
building MemoryEfficientAttnBlock with 512 in_channels...
--- using zero snr---
/home/ubuntu/ComfyUI/custom_nodes/ComfyUI-3D-Pack/crm/imagedream/ldm/interface.py:116: RuntimeWarning: divide by zero encountered in divide
  "sqrt_recip_alphas_cumprod", to_torch(np.sqrt(1.0 / alphas_cumprod))
/home/ubuntu/ComfyUI/custom_nodes/ComfyUI-3D-Pack/crm/imagedream/ldm/interface.py:119: RuntimeWarning: divide by zero encountered in divide
  "sqrt_recipm1_alphas_cumprod", to_torch(np.sqrt(1.0 / alphas_cumprod - 1))
Killed

[DenisKochetov]

I like the shape of the mesh more than TripoSR, but texturing looks poor