vita-epfl/CODE
Implementation of CODE: Confident Ordinary Differential Editing
This tool helps creative professionals and researchers enhance or transform images by using imperfect or 'out-of-distribution' guidance images, like rough sketches or low-quality photos. It takes an input image and a guidance image, then produces a high-quality, edited image that balances realism with the original guidance. Anyone working with image generation and editing, such as graphic designers or researchers in computer vision, would find this useful.
No commits in the last 6 months.
Use this if you need to refine or creatively edit images using guidance that might not be perfectly aligned or high-quality, ensuring the output maintains both realism and fidelity to your input.
Not ideal if your primary goal is simple, quick image adjustments without needing advanced generative model capabilities or handling out-of-distribution guidance.
Stars
8
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/vita-epfl/CODE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bytedance/InfiniteYou
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
River-Zhang/ICEdit
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image...
muzishen/IMAGHarmony
🧩 IMAGHarmony 🧩: Controllable image editing with consistent object quantity and layout. A...
AMAP-ML/FE2E
[CVPR 2026] Beyond Generation: Advancing Image Editing Priors for Depth and Normal Estimation
TencentARC/BrushNet
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting...