Text-to-Video
Diffusers
Safetensors
MiniMax H3
MiniMaxH3ModularPipeline
image-to-video
audio-video-generation
sparse-attention
block-sparse
inference-acceleration
triton
comfyui
Instructions to use Aazeus/Spark-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Aazeus/Spark-H3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Aazeus/Spark-H3", 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
Download __init__.py from Aazeus/Spark-H3: direct link, hf CLI and curl.
- Browser
- Download file 408 Bytes
-
https://huggingface.co/Aazeus/Spark-H3/resolve/main/__init__.py
- Command line
-
hf download hf://Aazeus/Spark-H3/__init__.py
-
curl -L -o __init__.py https://huggingface.co/Aazeus/Spark-H3/resolve/main/__init__.py
408 Bytes
| """ComfyUI entry point for the Spark-H3 custom node.""" | |
| if __package__: | |
| from .comfyui_nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS | |
| else: # pytest/importlib may load a custom-node root as ``__init__``. | |
| from comfyui_nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS | |
| WEB_DIRECTORY = "./web" | |
| __all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS", "WEB_DIRECTORY"] | |