Text-to-Video
Diffusers
English
RefMod
ref2vid
t2v
photorealistic
woman
celebrity
likeness
MiniMax-H3
Instructions to use pmczip/MiniMaxH3_RefMod with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use pmczip/MiniMaxH3_RefMod with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("pmczip/MiniMaxH3_RefMod", dtype=torch.bfloat16, device_map="cuda") prompt = "Aimee Teegarden (Video + Audio)" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Delete mmh3_Images
Browse files
mmh3_Images/vlcsnap-2026-11-09-16h23m09s464.png
DELETED
Git LFS Details
|
mmh3_Images/vlcsnap-2026-11-09-16h26m35s680.png
DELETED
Git LFS Details
|
mmh3_Images/vlcsnap-2026-11-09-16h27m39s747.png
DELETED
Git LFS Details
|
mmh3_Images/vlcsnap-2026-11-09-16h29m34s578.png
DELETED
Git LFS Details
|