search

Suzie1 / ComfyUI_Comfyroll_CustomNodes

Custom nodes for SDXL and SD1.5 including Multi-ControlNet, LoRA, Aspect Ratio, Process Switches, and many more nodes.
https://civitai.com/models/183551/comfyui-comfyroll-custom-nodes
502 stars 68 forks source link

Model merge Bug #142

Open kakachiex2 opened 3 months ago

kakachiex2 commented 3 months ago

I'm getting this error when using CR Model Merge workflow, it wasn't happening before yesterday start see this error.

Screenshot 2024-03-20 204656

WARNING SHAPE MISMATCH diffusion_model.output_blocks.7.0.in_layers.2.weight WEIGHT NOT MERGED torch.Size([320, 640, 3, 3]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.7.0.in_layers.2.weight WEIGHT NOT MERGED torch.Size([320, 640, 3, 3]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.7.0.emb_layers.1.weight WEIGHT NOT MERGED torch.Size([320, 1280]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.7.0.emb_layers.1.weight WEIGHT NOT MERGED torch.Size([320, 1280]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.7.0.out_layers.3.weight WEIGHT NOT MERGED torch.Size([320, 320, 3, 3]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.7.0.out_layers.3.weight WEIGHT NOT MERGED torch.Size([320, 320, 3, 3]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.7.0.skip_connection.weight WEIGHT NOT MERGED torch.Size([320, 640, 1, 1]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.7.0.skip_connection.weight WEIGHT NOT MERGED torch.Size([320, 640, 1, 1]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.8.0.in_layers.2.weight WEIGHT NOT MERGED torch.Size([320, 640, 3, 3]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.8.0.in_layers.2.weight WEIGHT NOT MERGED torch.Size([320, 640, 3, 3]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.8.0.emb_layers.1.weight WEIGHT NOT MERGED torch.Size([320, 1280]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.8.0.emb_layers.1.weight WEIGHT NOT MERGED torch.Size([320, 1280]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.8.0.out_layers.3.weight WEIGHT NOT MERGED torch.Size([320, 320, 3, 3]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.8.0.out_layers.3.weight WEIGHT NOT MERGED torch.Size([320, 320, 3, 3]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.8.0.skip_connection.weight WEIGHT NOT MERGED torch.Size([320, 640, 1, 1]) != torch.Size([320]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.8.0.skip_connection.weight WEIGHT NOT MERGED torch.Size([320, 640, 1, 1]) != torch.Size([320])

kakachiex2 commented 3 months ago

I have multi lora stack too WARNING SHAPE MISMATCH diffusion_model.output_blocks.5.1.proj_in.weight WEIGHT NOT MERGED torch.Size([1280, 1280, 1, 1]) != torch.Size([640]) ERROR lora diffusion_model.output_blocks.5.1.proj_in.weight shape '[640]' is invalid for input of size 409600 ERROR lora diffusion_model.output_blocks.5.1.proj_in.weight shape '[640]' is invalid for input of size 409600 ERROR lokr diffusion_model.output_blocks.5.1.proj_in.weight shape '[640]' is invalid for input of size 409600 ERROR lora diffusion_model.output_blocks.5.1.proj_in.weight shape '[640]' is invalid for input of size 409600 ERROR lora diffusion_model.output_blocks.5.1.proj_in.weight shape '[640]' is invalid for input of size 409600 ERROR lora diffusion_model.output_blocks.5.1.proj_in.weight shape '[640]' is invalid for input of size 409600 WARNING SHAPE MISMATCH diffusion_model.output_blocks.5.1.proj_in.weight WEIGHT NOT MERGED torch.Size([1280, 1280, 1, 1]) != torch.Size([640, 640]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.5.1.transformer_blocks.0.norm1.weight WEIGHT NOT MERGED torch.Size([1280]) != torch.Size([640]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.5.1.transformer_blocks.0.norm1.weight WEIGHT NOT MERGED torch.Size([1280]) != torch.Size([640]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_q.weight WEIGHT NOT MERGED torch.Size([1280, 1280]) != torch.Size([640, 640]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_k.weight WEIGHT NOT MERGED torch.Size([1280, 1280]) != torch.Size([640, 640]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_v.weight WEIGHT NOT MERGED torch.Size([1280, 1280]) != torch.Size([640, 640]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight WEIGHT NOT MERGED torch.Size([640, 640]) != torch.Size([640]) WARNING SHAPE MISMATCH diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight WEIGHT NOT MERGED torch.Size([1280, 1280]) != torch.Size([640]) ERROR lora diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight shape '[640]' is invalid for input of size 409600

kakachiex2 commented 3 months ago

During the generation process it throw all this errors it generates the first image but when I generate again it create a noised image.

https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/assets/1762112/9267776c-726f-47d7-9db7-7d15b5b55e9d

kakachiex2 commented 3 months ago

This behavior happens with all model merge node including CRModel merge this wasn't happening before