FusionBrainLab/Guide-and-Rescale
Official Implementation for "Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing"
This project helps graphic designers and digital artists quickly and easily modify existing real-world images. You provide an original image and a text description of the desired edit, and it produces a high-quality, modified image that preserves the original's essential structure and unedited areas. It's designed for creative professionals who need efficient, consistent image manipulation.
No commits in the last 6 months.
Use this if you need to perform precise, specific edits on real images using text prompts without extensive setup or fine-tuning, such as changing an object's color, adding an element, or modifying a background.
Not ideal if you're looking to generate entirely new images from scratch, as its primary purpose is editing existing photographs while maintaining their core integrity.
Stars
55
Forks
5
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Sep 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FusionBrainLab/Guide-and-Rescale"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation