Text-to-Video
Diffusers
Safetensors
MiniMax H3
video
audio
text-to-audio-video
distillation
dmd2
few-step
fastvideo
fasth3
Instructions to use FastVideo/FastVideo-Minimax-FastH3-Preview-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/FastVideo-Minimax-FastH3-Preview-v0.1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FastVideo/FastVideo-Minimax-FastH3-Preview-v0.1", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Rebrand to FastH3-Preview-v0.1 (README.md)
Browse files
README.md
CHANGED
|
@@ -15,9 +15,10 @@ tags:
|
|
| 15 |
- few-step
|
| 16 |
- minimax-h3
|
| 17 |
- fastvideo
|
|
|
|
| 18 |
---
|
| 19 |
|
| 20 |
-
#
|
| 21 |
|
| 22 |
**A few-step (4-step) distillation preview of [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3)**, the
|
| 23 |
33B dual-modality (video + audio) diffusion transformer — distilled with data-free
|
|
@@ -49,7 +50,7 @@ additional inference speedup.
|
|
| 49 |
from fastvideo import VideoGenerator
|
| 50 |
|
| 51 |
gen = VideoGenerator.from_pretrained(
|
| 52 |
-
"FastVideo/
|
| 53 |
num_gpus=1,
|
| 54 |
)
|
| 55 |
video = gen.generate_video(
|
|
|
|
| 15 |
- few-step
|
| 16 |
- minimax-h3
|
| 17 |
- fastvideo
|
| 18 |
+
- fasth3
|
| 19 |
---
|
| 20 |
|
| 21 |
+
# FastH3-Preview-v0.1
|
| 22 |
|
| 23 |
**A few-step (4-step) distillation preview of [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3)**, the
|
| 24 |
33B dual-modality (video + audio) diffusion transformer — distilled with data-free
|
|
|
|
| 50 |
from fastvideo import VideoGenerator
|
| 51 |
|
| 52 |
gen = VideoGenerator.from_pretrained(
|
| 53 |
+
"FastVideo/FastH3-Preview-v0.1",
|
| 54 |
num_gpus=1,
|
| 55 |
)
|
| 56 |
video = gen.generate_video(
|