Instructions to use tamnvvn/RORem with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tamnvvn/RORem with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import AutoPipelineForInpainting from diffusers.utils import load_image # switch to "mps" for apple devices pipe = AutoPipelineForInpainting.from_pretrained("tamnvvn/RORem", dtype=torch.float16, device_map="cuda") img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" image = load_image(img_url).resize((1024, 1024)) mask_image = load_image(mask_url).resize((1024, 1024)) prompt = "a tiger sitting on a park bench" generator = torch.Generator(device="cuda").manual_seed(0) image = pipe( prompt=prompt, image=image, mask_image=mask_image, guidance_scale=8.0, num_inference_steps=20, # steps between 15 and 30 work well for us strength=0.99, # make sure to use `strength` below 1.0 generator=generator, ).images[0] - Notebooks
- Google Colab
- Kaggle
Download model_index.json from tamnvvn/RORem: direct link, hf CLI and curl.
- Browser
- Download file 787 Bytes
-
https://huggingface.co/tamnvvn/RORem/resolve/main/model_index.json
- Command line
-
hf download hf://tamnvvn/RORem/model_index.json
-
curl -L -o model_index.json https://huggingface.co/tamnvvn/RORem/resolve/main/model_index.json
787 Bytes
| { | |
| "_class_name": "StableDiffusionXLInpaintPipeline", | |
| "_diffusers_version": "0.30.0", | |
| "_name_or_path": "diffusers/stable-diffusion-xl-1.0-inpainting-0.1", | |
| "feature_extractor": [ | |
| null, | |
| null | |
| ], | |
| "force_zeros_for_empty_prompt": true, | |
| "image_encoder": [ | |
| null, | |
| null | |
| ], | |
| "requires_aesthetics_score": false, | |
| "scheduler": [ | |
| "diffusers", | |
| "EulerDiscreteScheduler" | |
| ], | |
| "text_encoder": [ | |
| "transformers", | |
| "CLIPTextModel" | |
| ], | |
| "text_encoder_2": [ | |
| "transformers", | |
| "CLIPTextModelWithProjection" | |
| ], | |
| "tokenizer": [ | |
| "transformers", | |
| "CLIPTokenizer" | |
| ], | |
| "tokenizer_2": [ | |
| "transformers", | |
| "CLIPTokenizer" | |
| ], | |
| "unet": [ | |
| "diffusers", | |
| "UNet2DConditionModel" | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderKL" | |
| ] | |
| } | |