Instructions to use j-min/reco_sd14_coco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use j-min/reco_sd14_coco with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("j-min/reco_sd14_coco", dtype=torch.bfloat16, device_map="cuda") prompt = "A box contains six donuts with varying types of glazes and toppings. <|endoftext|> <bin514> <bin575> <bin741> <bin765> <|startoftext|> chocolate donut. <|endoftext|> <bin237> <bin517> <bin520> <bin784> <|startoftext|> dark vanilla donut. <|endoftext|> <bin763> <bin575> <bin988> <bin745> <|startoftext|> donut with sprinkles. <|endoftext|> <bin234> <bin281> <bin524> <bin527> <|startoftext|> donut with powdered sugar. <|endoftext|> <bin515> <bin259> <bin767> <bin514> <|startoftext|> pink donut. <|endoftext|> <bin753> <bin289> <bin958> <bin506> <|startoftext|> brown donut. <|endoftext|>" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download vae/diffusion_pytorch_model.bin from j-min/reco_sd14_coco: direct link, hf CLI and curl.
- Browser
- Download file 335 MB
-
https://huggingface.co/j-min/reco_sd14_coco/resolve/main/vae/diffusion_pytorch_model.bin
- Command line
-
hf download hf://j-min/reco_sd14_coco/vae/diffusion_pytorch_model.bin
-
curl -L -o diffusion_pytorch_model.bin https://huggingface.co/j-min/reco_sd14_coco/resolve/main/vae/diffusion_pytorch_model.bin
335 MB
- Xet hash:
- 5808e07a77682258cf0bb38585b8896453006a61ee301f79bd76545604968237
- Size of remote file:
- 335 MB
- SHA256:
- 2e4dc8eb6c3af767259a4a1ad01aaee61fa93a31fdf0dcf3d34c1db4b0ea6bd8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.