Skip to content

Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc.

License

Notifications You must be signed in to change notification settings

GeeMoose/EditAnything

Β 
Β 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Edit Anything by Segment-Anything

HuggingFace space

This is an ongoing project aims to Edit and Generate Anything in an image, powered by Segment Anything, ControlNet, BLIP2, Stable Diffusion, etc.

Any forms of contribution and suggestion are very welcomed!

NewsπŸ”₯

2023/06/09 - Support cross-image region drag and merge, unleash creative fusion!

2023/05/24 - Support multiple high-quality character editing: clothes, haircut, colored contact lenses.

2023/05/22 - Support sketch to image by adjusting mask align strength in sketch2image.py!

2023/05/13 - Support interactive segmentation with click operation!

2023/05/11 - Support tile model for detail refinement!

2023/05/04 - New demos of Beauty/Handsome Edit/Generation is released!

2023/05/04 - ControlNet-based inpainting model on any lora model is supported now. EditAnything can operate on any base/lord models without the requirements of inpainting model.

More update logs.

2023/05/01 - Models V0.4 based on Stable Diffusion 1.5/2.1 are released. New models are trained with more data and iterations.Model Zoo

2023/04/20 - We support the Customized editing with DreamBooth.

2023/04/17 - We support the SAM mask to semantic segmentation mask.

2023/04/17 - We support different alignment degrees bettween edited parts and the SAM mask, check it out on DEMO!

2023/04/15 - Gradio demo on Huggingface is released!

2023/04/14 - New model trained with LAION dataset is released.

2023/04/13 - Support pretrained model auto downloading and gradio in sam2image.py.

2023/04/12 - An initial version of text-guided edit-anything is in sam2groundingdino_edit.py(object-level) and sam2vlpart_edit.py(part-level).

2023/04/10 - An initial version of edit-anything is in sam2edit.py.

2023/04/10 - We transfer the pretrained model into diffusers style, the pretrained model is auto loaded when using sam2image_diffuser.py. Now you can combine our pretrained model with different base models easily!

2023/04/09 - We released a pretrained model of StableDiffusion based ControlNet that generate images conditioned by SAM segmentation.

Features

Try our HuggingFace DEMOπŸ”₯πŸ”₯πŸ”₯

Unleash creative fusion: Cross-image region drag and merge!πŸ”₯

image image

Clothes editing!πŸ”₯

image

Haircut editing!πŸ”₯

image

Colored contact lenses!πŸ”₯

image

Human replacement with tile refinement!πŸ”₯

image

Draw your Sketch and Generate your Image!πŸ”₯

prompt: "a paint of a tree in the ground with a river."

image image image
More demos.

prompt: "a paint, river, mountain, sun, cloud, beautiful field."

image image image

prompt: "a man, midsplit center parting hair, HD."

image image image

prompt: "a woman, long hair, detailed facial details, photorealistic, HD, beautiful face, solo, candle, brown hair, blue eye."

image image image

Also, you could use the generated image and sam model to refine your sketch definitely!

Generate/Edit your beauty!!!πŸ”₯πŸ”₯πŸ”₯

Edit Your beauty and Generate Your beauty

image image

Customized editing with layout alignment control.

image

EditAnything+DreamBooth: Train a customized DreamBooth Model with `tools/train_dreambooth_inpaint.py` and replace the base model in `sam2edit.py` with the trained model.

Image Editing with layout alignment control.

image

Keep the layout and Generate your season!

original paint SAM

Human Prompt: "A paint of spring/summer/autumn/winter field."

spring summer autumn winter

Edit Specific Thing by Text-Grounding and Segment-Anything

Editing by Text-guided Part Mask

Text Grounding: "dog head"

Human Prompt: "cute dog" p

More demos.

Text Grounding: "cat eye"

Human Prompt: "A cute small humanoid cat" p

Editing by Text-guided Object Mask

Text Grounding: "bench"

Human Prompt: "bench" p

Edit Anything by Segment-Anything

Human Prompt: "esplendent sunset sky, red brick wall" p

More demos.

Human Prompt: "chairs by the lake, sunny day, spring" p

Generate Anything by Segment-Anything

BLIP2 Prompt: "a large white and red ferry" p (1:input image; 2: segmentation mask; 3-8: generated images.)

More demos.

BLIP2 Prompt: "a cloudy sky" p

BLIP2 Prompt: "a black drone flying in the blue sky" p

  1. The human prompt and BLIP2 generated prompt build the text instruction.
  2. The SAM model segment the input image to generate segmentation mask without category.
  3. The segmentation mask and text instruction guide the image generation.

Generate semantic labels for each SAM mask.

p

python sam2semantic.py

Highlight features:

  • Pretrained ControlNet with SAM mask as condition enables the image generation with fine-grained control.
  • category-unrelated SAM mask enables more forms of editing and generation.
  • BLIP2 text generation enables text guidance-free control.

Setup

Create a environment

    conda env create -f environment.yaml
    conda activate control

Install BLIP2 and SAM

Put these models in models folder.

pip install git+https://github.com/huggingface/transformers.git

pip install git+https://github.com/facebookresearch/segment-anything.git

# For text-guided editing
pip install git+https://github.com/openai/CLIP.git

pip install git+https://github.com/facebookresearch/detectron2.git

pip install git+https://github.com/IDEA-Research/GroundingDINO.git

Download pretrained model

# Segment-anything ViT-H SAM model. 
cd models/
wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth

# BLIP2 model will be auto downloaded.

# Part Grounding Swin-Base Model.
wget https://github.com/Cheems-Seminar/segment-anything-and-name-it/releases/download/v1.0/swinbase_part_0a0000.pth

# Grounding DINO Model.
wget https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha2/groundingdino_swinb_cogcoor.pth

# Get pretrained model from huggingface. 
# No need to download this! But please install safetensors for reading the ckpt.

Run Demo

python sam2image.py
# or 
python sam2edit.py
# or
python sam2vlpart_edit.py
# or
python sam2groundingdino_edit.py

Set 'use_gradio = True' in these files if you have GUI to run the gradio demo.

Model Zoo

Model Features Download Path
SAM Pretrained(v0-1) Good Nature Sense shgao/edit-anything-v0-1-1
LAION Pretrained(v0-3) Good Face shgao/edit-anything-v0-3
LAION Pretrained(v0-4) Support StableDiffusion 1.5/2.1, More training data and iterations, Good Face shgao/edit-anything-v0-4-sd15 shgao/edit-anything-v0-4-sd21

Training

  1. Generate training dataset with dataset_build.py.
  2. Transfer stable-diffusion model with tool_add_control_sd21.py.
  3. Train model with sam_train_sd21.py.

Acknowledgement

This project is based on:

Segment Anything, ControlNet, BLIP2, MDT, Stable Diffusion, Large-scale Unsupervised Semantic Segmentation, Grounded Segment Anything: From Objects to Parts, Grounded-Segment-Anything

Thanks for these amazing projects!

About

Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.9%
  • Shell 0.1%