Instructions to use cocktailpeanut/jojo-dev2pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use cocktailpeanut/jojo-dev2pro with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("cocktailpeanut/jojo-dev2pro") prompt = "two people playing chess, jojo style" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download dataset.toml from cocktailpeanut/jojo-dev2pro: direct link, hf CLI and curl.
- Browser
- Download file 288 Bytes
-
https://huggingface.co/cocktailpeanut/jojo-dev2pro/resolve/main/dataset.toml
- Command line
-
hf download hf://cocktailpeanut/jojo-dev2pro/dataset.toml
-
curl -L -o dataset.toml https://huggingface.co/cocktailpeanut/jojo-dev2pro/resolve/main/dataset.toml
288 Bytes
| [general] | |
| shuffle_caption = false | |
| caption_extension = '.txt' | |
| keep_tokens = 1 | |
| [[datasets]] | |
| resolution = 512 | |
| batch_size = 1 | |
| keep_tokens = 1 | |
| [[datasets.subsets]] | |
| image_dir = 'C:\pinokio\api\fluxgym.git\datasets\jojo-dev2pro' | |
| class_tokens = 'jojo style' | |
| num_repeats = 7 |