diffusion-models

A collection of resources on controllable generation with text-to-image diffusion models.

A nice ML framework based on Jax/Flax. Continuation of https://github.com/AshishKumar4/FlaxDiff

Many Ways to Make and Modify Myriad Networks

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

Official Implementation of "DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models"

Open-source inference engine that runs language, vision, speech, image and video models from one container format, with a PyTorch and a Triton compute branch. Released for NVIDIA GPUs and CPU; Apple Silicon in progress.

Builds talking-head videos from one photo and a script, fully on your own machine.

Efficient Stable Diffusion Fine-Tuning Framework 2026: Lightweight Config-Driven Pipeline

Daily arXiv papers on efficient LLMs and visual generation: quantization, pruning, distillation, KV cache, speculative decoding, serving systems, and diffusion acceleration.

This repository implements an automated crawling tool for topics about "data mining" papers from the arXiv preprint website.

ComfyUI-DaVinci-MagiHuman 2026: Fast AI Video & Audio Nodes 🚀

AI Sketch Assistant 2026 🎨 - Free Interactive Art Generator & Tools

Sim2Real Diffusion: Learning Cross-Domain Adaptive Representations for Transferable Autonomous Driving

Diffusion-pretrained vision foundation models for multi-crop plant phenotyping: organ segmentation, crop–weed parsing, depth estimation, and counting.

Seamless 360° panoramas from stock Stable Diffusion v1.5: a from-scratch MultiDiffusion sampler with circular windows and multi-branch prompts. Seam ratio 1.12 over 28 panoramas, no training.

Native macOS app for MiniMax-H3 (text/image/video-to-video-with-audio diffusion) on Apple Silicon — Metal/MPSGraph only, no Python or cloud calls.

A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control

Guía técnica en español de las arquitecturas de IA: qué son, para qué sirven y cómo funcionan, con ejemplos en PyTorch

Train LoRAs for Qwen-Image 2.1, FLUX.2 Klein 9B, FLUX.3 Image Klein, Krea 2, Z-Image, MOSS-Image, ERNIE-Image, Ideogram 4, Anima, SDXL (Pony, Illustrious, NoobAI), LTX 2.3, MiniMax-H3, and more on NVIDIA GPUs from 4–8 GB VRAM. One install, one launcher, NF4 models. Windows, Linux and RunPod.