Text-to-Image
MiniMax H3
Diffusers
Safetensors
English
image-to-image
image-editing
image-generation
Instructions to use MiniMaxAI/MiniMax-H3-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MiniMaxAI/MiniMax-H3-Image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3-Image", 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 vae/config.json from MiniMaxAI/MiniMax-H3-Image: direct link, hf CLI and curl.
- Browser
- Download file 1.83 kB
-
https://huggingface.co/MiniMaxAI/MiniMax-H3-Image/resolve/main/vae/config.json
- Command line
-
hf download hf://MiniMaxAI/MiniMax-H3-Image/vae/config.json
-
curl -L -o config.json https://huggingface.co/MiniMaxAI/MiniMax-H3-Image/resolve/main/vae/config.json
1.83 kB
| { | |
| "_class_name": "MiniMaxH3ImageVAE", | |
| "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, | |
| 1.6831774711608887, | |
| 1.7549455165863037, | |
| 1.5636216402053833, | |
| 2.194143533706665, | |
| 0.9653137922286987, | |
| 1.0569885969161987, | |
| 0.841948926448822, | |
| 0.7729952931404114, | |
| 1.8955937623977661, | |
| 0.946841835975647, | |
| 0.7996809482574463, | |
| 0.44988900423049927, | |
| 0.7197399735450745, | |
| 0.6936293244361877, | |
| 2.961095094680786, | |
| 2.7694199085235596, | |
| 3.0496184825897217, | |
| 2.1088054180145264, | |
| 3.276226282119751, | |
| 3.1627357006073, | |
| 2.2816812992095947, | |
| 2.6127843856811523 | |
| ], | |
| "vae_chunk_dim": -1, | |
| "vae_clip_length": 17, | |
| "vae_decoder_tiling": 1, | |
| "vae_encoder_tiling": 1, | |
| "vae_parallel_tiling": 0, | |
| "vae_tile_overlap_min": 64, | |
| "vae_tile_size": 256, | |
| "vae_token_drop": 0, | |
| "vit_decoder_2d": true, | |
| "vit_decoder_kwargs": { | |
| "dim_head": 64, | |
| "ffn_activation_fn": "silu", | |
| "ffn_use_gated": true, | |
| "heads": 16, | |
| "norm_affine": true, | |
| "norm_type": "rms_norm", | |
| "num_layers": 24, | |
| "qk_norm_affine": false, | |
| "qk_norm_type": "rms_norm", | |
| "rope_dim_ratio": 0.5, | |
| "rope_theta": 100.0 | |
| } | |
| } | |