Still needs my Adaln node to apply correctly.
you still need my adaln lora fix node after yours for the keys to be appllied correctly. otherwise
ERROR] ERROR lora diffusion_model.blocks.0.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.1.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.2.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.3.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.4.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
Yeah I tested with the unpruned model, I tried with your node+pruned and it worked
Yeah I tested with the unpruned model, I tried with your node+pruned and it worked
might want to mention about pruned vs unpruned so people don't think it's broken.
I'm working on a patch now, should be out shortly. Appreciate you testing!
I used your LoRa and corresponding load nodes, including the workflow, but when running it in ComfyUI, I encountered numerous LoRa errors:
minimax_h3_fl2va_pdd_acc_8step_comfyui.safetensors
minimax_h3_ref2va_pdd_acc_8step_comfyui.safetensors
This means they appear to be failing to work as expected.
[ERROR] ERROR lora diffusion_model.blocks.1.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.2.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.3.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.4.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.5.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.6.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.7.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.8.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.9.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.10.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
[ERROR] ERROR lora diffusion_model.blocks.11.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
I added support for the pruned models here: https://github.com/Jalen-Brunson/ComfyUI-MiniMax-H3-PDD-Acc/
That should fix the issue you're encountering.