Image-Text-to-Video
Diffusers
Safetensors
text-to-video
image-to-video
video-to-video
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
video-to-audio-video
audio-to-audio-video
audio-video-generation
multimodal
synchronized-audio-video
reference-to-audio-video
Instructions to use Green-eyedDevil/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Green-eyedDevil/MiniMax-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("Green-eyedDevil/MiniMax-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
| { | |
| "_class_name": "MiniMaxH3VideoVAE", | |
| "_diffusers_version": "0.32.2", | |
| "mode": "standalone", | |
| "auto_map": { | |
| "AutoModel": "minimax_h3_video_vae.MiniMaxH3VideoVAE" | |
| }, | |
| "source_path": "source", | |
| "source_class_name": "AutoencoderKLLegacy", | |
| "vae_clip_length": 17, | |
| "vae_token_drop": 3, | |
| "vae_encoder_tiling": 1, | |
| "vae_decoder_tiling": 1, | |
| "vae_parallel_tiling": 1, | |
| "vae_tile_size": 256, | |
| "vae_tile_overlap_min": 64, | |
| "vae_encoder_parallel": 0, | |
| "vae_decoder_parallel": 0, | |
| "vae_chunk_dim": -1, | |
| "source_safetensors_path": "model.safetensors", | |
| "latent_channels": 24, | |
| "latents_mean": [ | |
| 0.858090341091156, | |
| -0.9606591463088989, | |
| 1.0661640167236328, | |
| -0.5090325474739075, | |
| -0.2727581858634949, | |
| -1.3675414323806763, | |
| -0.2553254961967468, | |
| -0.26907554268836975, | |
| -0.5376840829849243, | |
| -0.0464097298681736, | |
| 0.6657370328903198, | |
| 0.19690127670764923, | |
| -0.5460608005523682, | |
| -0.4035342037677765, | |
| -0.23683024942874908, | |
| 0.25928452610969543, | |
| -0.30133944749832153, | |
| 0.211341992020607, | |
| -1.1206848621368408, | |
| 0.3581933379173279, | |
| -0.04225143790245056, | |
| 0.2604829967021942, | |
| 0.22864092886447906, | |
| 0.7056031823158264 | |
| ], | |
| "latents_std": [ | |
| 1.2223774194717407, | |
| 1.2767263650894165, | |
| 1.68317747116088865, | |
| 1.7549455165863037, | |
| 1.5636216402053833, | |
| 2.194143533706665, | |
| 0.96531379222869875, | |
| 1.05698859691619875, | |
| 0.841948926448822, | |
| 0.7729952931404114, | |
| 1.8955937623977661, | |
| 0.946841835975647, | |
| 0.7996809482574463, | |
| 0.44988900423049925, | |
| 0.7197399735450745, | |
| 0.69362932443618775, | |
| 2.961095094680786, | |
| 2.7694199085235595, | |
| 3.0496184825897215, | |
| 2.1088054180145265, | |
| 3.276226282119751, | |
| 3.1627357006073, | |
| 2.28168129920959475, | |
| 2.6127843856811525 | |
| ] | |
| } | |