Image-Text-to-Video
Diffusers
Safetensors
text-to-video
image-to-video
audio-video-generation
runpod
Instructions to use ovedrive/MiniMax-H3-generator-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ovedrive/MiniMax-H3-generator-bf16 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ovedrive/MiniMax-H3-generator-bf16", 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
Correct slim cache model card
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ tags:
|
|
| 14 |
|
| 15 |
# MiniMax H3 BF16 generator subset
|
| 16 |
|
| 17 |
-
This is a slim, unquantized BF16 generator cache derived from MiniMaxAI/MiniMax-H3 for
|
| 18 |
|
| 19 |
It contains transformer, vae, audio_vae, scheduler, audio_scheduler, and modular_model_index.json. The external H3 conditioner is intentionally not included and is called through its existing Hugging Face Space API.
|
| 20 |
|
|
|
|
| 14 |
|
| 15 |
# MiniMax H3 BF16 generator subset
|
| 16 |
|
| 17 |
+
This is a slim, unquantized BF16 generator cache derived from MiniMaxAI/MiniMax-H3 for a split RunPod worker. The model-card text has been modified to describe this subset.
|
| 18 |
|
| 19 |
It contains transformer, vae, audio_vae, scheduler, audio_scheduler, and modular_model_index.json. The external H3 conditioner is intentionally not included and is called through its existing Hugging Face Space API.
|
| 20 |
|