metadata
license: apache-2.0
base_model:
- MiniMaxAI/MiniMax-H3
- lightx2v/Minimax-h3-Turbo
base_model_relation: adapter
pipeline_tag: image-text-to-video
tags:
- lora
- t2v
- i2v
- comfyui
- minimax-h3
Contents
| file | size |
|---|---|
loras/minimax_h3_fl2v_lightx2v_turbo_8step_merge_0821_bf16.safetensors |
1.96 GB |
FLFV 8 Step Merge 0821
| source | weight |
|---|---|
minimax_h3_fl2v_turbo_4step_v1.1_768p_comfyui_bf16.safetensors |
0.5 |
minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors |
1.0 |
The 4 step LoRA was trained using shift 6 and the 8 step was trained using shift 12. I made this merge to use as a video refiner only so I recommend using v1.1 on its own for a fresh generation. If you want to try using this for a full generation, use shift 6, 8 steps and 1.0 strength.