diffusion-models

Scalable group inference for generating high quality and diverse images with diffusion models.

Generating figures from research papers, using textual captions from the paper.

A repo that attempts to train stable diffusion 3 from scratch

A curated list of recent papers (2023–2025) on controllable generative models, covering diffusion-based architectures with fine-grained control, attention interpretation, spectral manipulation, and structure-preserving image editing. Ideal for researchers and developers exploring controllable synthesis.

A simple and intuitive library for diffusion models using Flax and Jax. Includes detailed notebooks on DDPM, DDIM, and EDM with simplified mathematical explanations. Made as part of my journey for learning and experimenting with generative AI.

A High Quality (HD / 2K / 4K) Image Generation Using Stable Diffusion and Real-ESR / SwinIR /GFPGAN

Multimodal generative AI resources : talking heads, STT, TTS, image & video generation, and AI Agent

[ICML 2024] Code for the paper "Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases"

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, TUI, iPhone, REST/SSE, and MCP.

Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)

Official implementation of "Divide & Bind Your Attention for Improved Generative Semantic Nursing" (BMVC 2023 Oral)

Finetune HunyuanImage 3.0, a 80B unified understanding and generation model

[CVPR '23] Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models

✨ PyTorch implementation of "Cora: Correspondence-aware Image Editing Using Few-Step Diffusion", accepted at SIGGRAPH 2025.

PlantDreamer: Achieving Realistic 3D Plant Models with Diffusion-Guided Gaussian Splatting [CVPPA: ICCVW 2025]

ReNeg: Learning Negative Embedding with Reward Guidance

🔥 (SIGGRAPH 2026) 3D-aware hairstyle transfer for images: in-context bald conversion, pose-aligned hair import, and identity-preserving synthesis.

Think.ai hackathon winner project : Moroccan interior design generator

[ECCV'24] MaxFusion: Plug & Play multimodal generation in text to image diffusion models

Building an Image-to-Video (I2V) Model from Scratch