Text-to-Video
Diffusers
English
RefMod
ref2vid
t2v
photorealistic
woman
celebrity
likeness
MiniMax-H3
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 = "Alex Kingston (Video + Audio)"
image = pipe(prompt).images[0]MiniMax H3 RefMods
=====================
- Prompt
- Alex Kingston (Video + Audio)
- Prompt
- Lacey Chabert (Video + Audio)
- Prompt
- Laura Prepon (Video + Audio)
- Prompt
- Melissa Joan Hart (Video + Audio)
Current MiniMax H3 RefMods:
Alex Kingston - 413xkin65t0n (Video + Audio)
Lacey Chabert - 14c3ych4b3rt (Video + Audio)
Laura Prepon - 14ur4pr3p0n (Video + Audio)
Melissa Joan Hart - m31j04nh4rt (Video + Audio)
- Downloads last month
- 112
Model tree for pmczip/MiniMaxH3_RefMod
Base model
MiniMaxAI/MiniMax-H3