Image-to-Video
Diffusers
Safetensors
MiniMax H3
English
smd
diffusion-distillation
few-step
lora
minimax
video-generation
audio-video
4-step
reference-to-video
Instructions to use zjwfufu/SMD-MiniMax-H3-Ref2VA-4step with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zjwfufu/SMD-MiniMax-H3-Ref2VA-4step with Diffusers:
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("zjwfufu/SMD-MiniMax-H3-Ref2VA-4step") 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") output = pipe(image=input_image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Download examples/sample.mp4 from zjwfufu/SMD-MiniMax-H3-Ref2VA-4step: direct link, hf CLI and curl.
- Browser
- Download file 689 kB
-
https://huggingface.co/zjwfufu/SMD-MiniMax-H3-Ref2VA-4step/resolve/main/examples/sample.mp4
- Command line
-
hf download hf://zjwfufu/SMD-MiniMax-H3-Ref2VA-4step/examples/sample.mp4
-
curl -L -o sample.mp4 https://huggingface.co/zjwfufu/SMD-MiniMax-H3-Ref2VA-4step/resolve/main/examples/sample.mp4
689 kB
- Xet hash:
- 446e400e2f2e1878eece925ac82e34d067e1dcb5104929780202a3ee798bdd85
- Size of remote file:
- 689 kB
- SHA256:
- 6d9fda48b9b5b5cc331b22f5aa4994c12d20a3a110759f75f111561e70a8beb6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.