WisconsinAIVision/visii
👀 Visual Instruction Inversion: Image Editing via Visual Prompting (NeurIPS 2023)
This tool helps graphic designers, digital artists, and marketers apply a specific visual editing style from one pair of images to many new images. You provide an original image and its 'after' version (e.g., a photo of a dog and the same dog in a watercolor style). The tool learns this transformation and then applies that exact style to other images you provide, effectively automating consistent visual branding or artistic effects.
No commits in the last 6 months.
Use this if you need to replicate a unique image editing style or transformation across many different images consistently, especially for artistic effects or brand-specific visual treatments.
Not ideal if you need precise pixel-level control or if your editing task requires complex, multi-step manipulations that can't be learned from a single before-and-after example.
Stars
96
Forks
3
Language
Python
License
—
Category
Last pushed
Dec 19, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/WisconsinAIVision/visii"
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...