zelaki/ReDi
[NeurIPS'25 Spotlight] Boosting Generative Image Modeling via Joint Image-Feature Synthesis
This tool helps researchers and practitioners in generative AI create highly realistic images by blending traditional image generation with a novel approach that leverages feature representations. You provide the model with an input image dataset, and it generates new, diverse images that maintain high fidelity and quality. It's designed for those pushing the boundaries of image synthesis and large-scale visual content creation.
115 stars.
Use this if you are working on advanced image generation tasks and need to produce synthetic images with exceptional quality and diversity.
Not ideal if you are looking for a simple, out-of-the-box solution for basic image editing or small-scale image manipulation.
Stars
115
Forks
4
Language
Python
License
—
Category
Last pushed
Nov 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zelaki/ReDi"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...