Hugging Face's logo

rzgar
/
minimax-h3_fl2v_8Step_motion_enhancer

Image-to-Video
Diffusers
text-to-video
image-text-to-video
video-to-video
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
video-to-audio-video
audio-to-audio-video
audio-video-generation
multimodal
synchronized-audio-video
reference-to-audio-video
lora
template:diffusion-lora
Model card Files
xet
 Community
3
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image, export_to_video

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("rzgar/minimax-h3_fl2v_8Step_motion_enhancer")

prompt = "A man with short gray hair plays a red electric guitar."
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png")

image = pipe(image=input_image, prompt=prompt).frames[0]
export_to_video(output, "output.mp4")

MiniMax-H3 FL2V 8-Step Motion Enhancer

Model description

An 8-step LoRA for the MiniMax-H3 FL2VS video model, built on top of the vanilla LightX2V 8-step LoRA.

It focuses on the NSFW side of generation:

  • More accurate male and female anatomy
  • Understands NSFW-related motions and enhances the animations

Files

Acknowledgements

LightX2V

Download model

Download them in the Files & versions tab.

Downloads last month
2,412
Inference Providers NEW
Image-to-Video

Model tree for rzgar/minimax-h3_fl2v_8Step_motion_enhancer

Base model

MiniMaxAI/MiniMax-H3
Adapter
(60)
this model

Space using rzgar/minimax-h3_fl2v_8Step_motion_enhancer 1

Collection including rzgar/minimax-h3_fl2v_8Step_motion_enhancer