metadata
license: apache-2.0
base_model:
- Comfy-Org/MiniMax-H3
MiniMax-H3-Ref-Patch
By extracting 112 keys related to the keywords:
adaln_proj
condition_proj
video_patch_proj
audio_patch_proj
final_layer.audio_out
final_layer.video_out
from ref2va and fl2va weights and storing their differences as patches, we can use ~140MB of data to make fl2va mimic the behavior and output quality of ref2va to some extent.
- You need to use comfyui extension "ComfyUI-MiniMaxH3_Ref-Patch" to load this patch.
- The goal of this project is not to replicate the behavior of ref2v, but to simulate the effect of KJ's LoRA