Instructions to use tiny-random/minimax-h3-image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tiny-random/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("tiny-random/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
- Local Apps Settings
- Draw Things
- DiffusionBee
Download modular_model_index.json from tiny-random/minimax-h3-image: direct link, hf CLI and curl.
- Browser
- Download file 1.89 kB
-
https://huggingface.co/tiny-random/minimax-h3-image/resolve/main/modular_model_index.json
- Command line
-
hf download hf://tiny-random/minimax-h3-image/modular_model_index.json
-
curl -L -o modular_model_index.json https://huggingface.co/tiny-random/minimax-h3-image/resolve/main/modular_model_index.json
1.89 kB
| { | |
| "_class_name": "MiniMaxH3ImageModularPipeline", | |
| "_blocks_class_name": "MiniMaxH3ImageBlocks", | |
| "_diffusers_version": "0.43.0", | |
| "sample_sigmas": [ | |
| 1.0, | |
| 0.9675236940383911, | |
| 0.8875485062599182, | |
| 0.75, | |
| 0.5327739119529724, | |
| 0.23200887441635132, | |
| 0.0 | |
| ], | |
| "reference_min_short_edge": 64, | |
| "reference_max_short_edge": 64, | |
| "vision_min_short_edge": 64, | |
| "vision_max_short_edge": 64, | |
| "text_encoder": [ | |
| "transformers", | |
| "Qwen3VLForConditionalGeneration", | |
| { | |
| "type_hint": [ | |
| "transformers", | |
| "Qwen3VLForConditionalGeneration" | |
| ], | |
| "pretrained_model_name_or_path": ".", | |
| "subfolder": "text_encoder" | |
| } | |
| ], | |
| "tokenizer": [ | |
| "transformers", | |
| "Qwen2TokenizerFast", | |
| { | |
| "type_hint": [ | |
| "transformers", | |
| "Qwen2TokenizerFast" | |
| ], | |
| "pretrained_model_name_or_path": ".", | |
| "subfolder": "tokenizer" | |
| } | |
| ], | |
| "processor": [ | |
| "transformers", | |
| "Qwen3VLProcessor", | |
| { | |
| "type_hint": [ | |
| "transformers", | |
| "Qwen3VLProcessor" | |
| ], | |
| "pretrained_model_name_or_path": ".", | |
| "subfolder": "processor" | |
| } | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderKLMiniMaxH3Image", | |
| { | |
| "type_hint": [ | |
| "diffusers", | |
| "AutoencoderKLMiniMaxH3Image" | |
| ], | |
| "pretrained_model_name_or_path": ".", | |
| "subfolder": "vae" | |
| } | |
| ], | |
| "transformer": [ | |
| "diffusers", | |
| "MiniMaxH3ImageTransformer2DModel", | |
| { | |
| "type_hint": [ | |
| "diffusers", | |
| "MiniMaxH3ImageTransformer2DModel" | |
| ], | |
| "pretrained_model_name_or_path": ".", | |
| "subfolder": "transformer" | |
| } | |
| ], | |
| "scheduler": [ | |
| "diffusers", | |
| "MiniMaxH3Scheduler", | |
| { | |
| "type_hint": [ | |
| "diffusers", | |
| "MiniMaxH3Scheduler" | |
| ], | |
| "pretrained_model_name_or_path": ".", | |
| "subfolder": "scheduler" | |
| } | |
| ] | |
| } | |