[ERROR] ERROR lora diffusion_model.blocks.0.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384
Using minimax_h3_turbo_4step.safetensors, turbo lora loader + turbo sampler.
You need to use one of the unpruned models.
https://huggingface.co/Comfy-Org/MiniMax-H3/tree/main/diffusion_models
https://huggingface.co/drbaph/MiniMax-H3-Turbo-Lora-ComfyUI
try this one if you want to use it with the pruned version
Dude, I had a similar problem, I solved it by doing this! Now it's working perfectly!
I replaced the LoRa with this converted version to run on ComfyUI, and it worked incredibly well. Very fast generation and with excellent quality! ( https://huggingface.co/QrusherZA/H3_Turbo_ComfyUI/tree/main ). Use the node "Power LoRa Loader".. I'm using a 720 x 720 resolution, 4 or 6 steps, and Euler - beta. Another tip to speed things up even more is to use the "spectrum apply minimax h3" node; it's amazing, it almost halves the generation time and has very little quality loss! ;)
https://huggingface.co/drbaph/MiniMax-H3-Turbo-Lora-ComfyUI
try this one if you want to use it with the pruned version
I tried, but that version seems not so good. 😣
Dude, I had a similar problem, I solved it by doing this! Now it's working perfectly!
I replaced the LoRa with this converted version to run on ComfyUI, and it worked incredibly well. Very fast generation and with excellent quality! ( https://huggingface.co/QrusherZA/H3_Turbo_ComfyUI/tree/main ). Use the node "Power LoRa Loader".. I'm using a 720 x 720 resolution, 4 or 6 steps, and Euler - beta. Another tip to speed things up even more is to use the "spectrum apply minimax h3" node; it's amazing, it almost halves the generation time and has very little quality loss! ;)
Thank you, where can I active "spectrum apply minimax h3" node?
edit: ok I found, I will try that later