Instructions to use NormalUhr/UnlearnCanvas-ckpts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use NormalUhr/UnlearnCanvas-ckpts with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("NormalUhr/UnlearnCanvas-ckpts", 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 diffusion/diffuser/style50/tokenizer/special_tokens_map.json from NormalUhr/UnlearnCanvas-ckpts: direct link, hf CLI and curl.
- Browser
- Download file 472 Bytes
-
https://huggingface.co/NormalUhr/UnlearnCanvas-ckpts/resolve/main/diffusion/diffuser/style50/tokenizer/special_tokens_map.json
- Command line
-
hf download hf://NormalUhr/UnlearnCanvas-ckpts/diffusion/diffuser/style50/tokenizer/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/NormalUhr/UnlearnCanvas-ckpts/resolve/main/diffusion/diffuser/style50/tokenizer/special_tokens_map.json
472 Bytes
| { | |
| "bos_token": { | |
| "content": "<|startoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": "<|endoftext|>", | |
| "unk_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |