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
Ctrl+K
- .github
- FL2VA
- Ref2VA
- assets
- audio_scheduler
- audio_vae
- comfyui
- docs
- h3_lbh
- h3_sparse_attention
- processor
- scheduler
- scripts
- skills
- sol_attn
- tests
- text_encoder
- tokenizer
- transformer
- transformer_ref
- vae
- web
- workflows
- 3.63 kB
- 126 Bytes
- 7.81 kB
- 11.4 kB
- 41.7 kB
- 40.2 kB
- 9.62 kB
- 36.9 kB
- 408 Bytes
- 9.66 kB
- 1.88 kB
- 44.2 kB
- 15.2 kB
- 2.94 kB
- 2.94 kB
- 876 Bytes
- 1.93 kB
- 287 Bytes
- 12.4 kB