omriav/blended-diffusion
Official implementation for "Blended Diffusion for Text-driven Editing of Natural Images" [CVPR 2022]
This project helps graphic designers, marketers, and content creators modify specific regions of natural images using simple text descriptions. You provide an existing image, highlight the area you want to change, and describe the desired edit (e.g., "add a rock"). The output is a new image with the specified region altered to match your text prompt, seamlessly blended into the original picture.
584 stars. No commits in the last 6 months.
Use this if you need to perform precise, localized edits on images, such as adding or removing objects, changing backgrounds, or altering existing elements, all guided by natural language.
Not ideal if you need real-time image editing or absolute pixel-level control over every detail, as it generates new content based on a prompt rather than offering traditional manual manipulation.
Stars
584
Forks
43
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/omriav/blended-diffusion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.