Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Diffusion models, image editing, upscaling and the surrounding creative tooling.
Signals: stable-diffusion, diffusion-models, image-generation, text-to-image, generative-art, comfyui, controlnet, flux
879 results
Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"
Official implementation for "Story2Board: A Training‑Free Approach for Expressive Storyboard Generation"
[CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
A paper collection of recent diffusion models for text-image generation tasks, e,g., visual text generation, font generation, text removal, text image super resolution, text editing, handwritten generation, scene text recognition and scene text detection.
Anti-DreamBooth: Protecting users from personalized text-to-image synthesis (ICCV 2023)
[ICCV 2025] VisualCloze: A universal image generation framework that can support a wide range of in-domain tasks and generalize to unseen ones. (🔥 🔥 🔥 Merged into offical pipelines of diffusers.)
[ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)
🔥 [ICCV 2025 Highlight] Official ComfyUI native node supporting InfiniteYou with FLUX
MinImagen: A minimal implementation of the Imagen text-to-image model
Getting the latest versions of Disco Diffusion to work locally, instead of colab. Including how I run this on Windows, despite some Linux only dependencies ;)
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints.
Colab notebook for Stable Diffusion Hyper-SDXL.
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
Implementation of Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models
[CVPR2022 oral] A Simple and Effective Baseline for Text-to-Image Synthesis
FIBO is a SOTA, first open-source, JSON-native text-to-image model built for controllable, predictable, and legally safe image generation.
[ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
[Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation
Official Repository of the paper "Trajectory Consistency Distillation"
Official GitHub repository for FLUX.1 Krea [dev].
Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.
[CVPR 2024] "MACE: Mass Concept Erasure in Diffusion Models" (Official Implementation)
End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
24,537 repositories in the index in total.
