Instructions to use ivanmikhnenkov/tinydit-256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ivanmikhnenkov/tinydit-256 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ivanmikhnenkov/tinydit-256", 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
Add diffusers format: TinyDiTPipeline + TinyDiTTransformer2DModel (remote code), bundled T5 and FLUX.2 VAE
1c18331 verified Download model_index.json from ivanmikhnenkov/tinydit-256: direct link, hf CLI and curl.
- Browser
- Download file 504 Bytes
-
https://huggingface.co/ivanmikhnenkov/tinydit-256/resolve/main/model_index.json
- Command line
-
hf download hf://ivanmikhnenkov/tinydit-256/model_index.json
-
curl -L -o model_index.json https://huggingface.co/ivanmikhnenkov/tinydit-256/resolve/main/model_index.json
504 Bytes
| { | |
| "_class_name": [ | |
| "pipeline_tinydit", | |
| "TinyDiTPipeline" | |
| ], | |
| "_diffusers_version": "0.42.0", | |
| "_ignore_files": [ | |
| "model.safetensors" | |
| ], | |
| "scheduler": [ | |
| "diffusers", | |
| "FlowMatchEulerDiscreteScheduler" | |
| ], | |
| "text_encoder": [ | |
| "transformers", | |
| "T5EncoderModel" | |
| ], | |
| "tokenizer": [ | |
| "transformers", | |
| "T5TokenizerFast" | |
| ], | |
| "transformer": [ | |
| "transformer_tinydit", | |
| "TinyDiTTransformer2DModel" | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderKLFlux2" | |
| ] | |
| } |