Instructions to use BiliSakura/MiniT2I-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/MiniT2I-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BiliSakura/MiniT2I-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "A lonely astronaut standing on a quiet beach under two moons." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download MiniT2I-B-16/model_index.json from BiliSakura/MiniT2I-diffusers: direct link, hf CLI and curl.
- Browser
- Download file 486 Bytes
-
https://huggingface.co/BiliSakura/MiniT2I-diffusers/resolve/main/MiniT2I-B-16/model_index.json
- Command line
-
hf download hf://BiliSakura/MiniT2I-diffusers/MiniT2I-B-16/model_index.json
-
curl -L -o model_index.json https://huggingface.co/BiliSakura/MiniT2I-diffusers/resolve/main/MiniT2I-B-16/model_index.json
486 Bytes
| { | |
| "_class_name": [ | |
| "pipeline", | |
| "MiniT2ITextToImagePipeline" | |
| ], | |
| "_diffusers_version": "0.32.0", | |
| "default_num_inference_steps": 100, | |
| "model_type": "b16", | |
| "recommended_guidance_scale": 2.5, | |
| "scheduler": [ | |
| "diffusers", | |
| "FlowMatchEulerDiscreteScheduler" | |
| ], | |
| "text_encoder": [ | |
| "transformers", | |
| "T5EncoderModel" | |
| ], | |
| "tokenizer": [ | |
| "transformers", | |
| "T5Tokenizer" | |
| ], | |
| "transformer": [ | |
| "transformer_minit2i", | |
| "MiniT2IMMJiTModel" | |
| ] | |
| } | |