Correr-Zhou/HiFi-Inpaint
[CVPR 2026] Offical implementation of the paper "HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images".
This tool helps advertisers, e-commerce professionals, and digital marketers create realistic human-product images for their campaigns. You provide an image of a person and a separate reference image of a product, and it generates a new image seamlessly integrating the product onto the person while preserving all product details. This is ideal for showcasing how products look when used or worn, enhancing visual marketing content.
Use this if you need to generate high-quality images that show a person interacting with or wearing a product, ensuring the product's details are perfectly maintained.
Not ideal if you need to generate images without a specific product reference or if your primary goal is general image manipulation not focused on product integration.
Stars
56
Forks
3
Language
—
License
Apache-2.0
Category
Last pushed
Mar 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Correr-Zhou/HiFi-Inpaint"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scraed/LanPaint
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
julienkay/com.doji.diffusers
A Unity package to run pretrained diffusion models with Unity Sentis
apapiu/transformer_latent_diffusion
Text to Image Latent Diffusion using a Transformer core
Aatricks/LightDiffusion-Next
Fastest Diffusion backend, WebUI, server. Pushing implementation and discovery of optimizations...
FMXExpress/Stable-Diffusion-Desktop-Client
Stable Diffusion Desktop client for Windows, macOS, and Linux built in Embarcadero Delphi.