lrzjason

comfy-model-tools. Utility scripts for packaging models for ComfyUI.

Nomi. Open-source, local-first desktop app for AI video creation: write a script → generate images & video → edit on a timeline → export. Bring your own model & API key — everything runs on your machine. Built with Electron + React.

GenClaw. GenClaw: Code-Driven Agentic Image Generation

SCOPE. Python

PiD. PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

oh-my-pi. ⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

skills. Skills for Real Engineers. Straight from my .agents directory.

LakonLab. Official implementation of AsymFlow, pi-Flow, GMFlow

D-OPSD. Official Repo of "D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models"

hello-agents. 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

HiDream-O1-Image. Python

ComfyUI_RH_OpenAPI. This is a ComfyUI plugin for https://www.runninghub.cn/call-api/standard-api

FD-Loss. Python

GMNet. [ICLR2025] Learning Gain Map for Inverse Tone Mapping

openexr-images. Collection of images associated with the OpenEXR distribution

SenseNova-U1. SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

Real-HDRV. CVPR 2024: Official repository of 'Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network'

agentscope. Build and run agents you can see, understand and trust.

ComfyUI_Gear. VFX-oriented nodes for ComfyUI: HDR LogC3 decode + interactive ACEScct color grading panel (color wheels, scopes, A|B compare, batch scrubber) powered by exr-viewer.

LumiPic. Single-Image HDR Reconstruction via LogC3-Encoded Diffusion Transformer LoRA

houtini-lm. MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.

ComfyUI-LCS. Python

LCS. [ICML 2026] The Latent Color Subspace: Emergent Order in High-Dimensional Chaos

QwenPaw. Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

UAE. Official repo for UAE [ECCV 2026]

mlx-drifting-model. Generative Modeling via Drifting in MLX

comfyui-node-organizer. Automatically align and organize nodes in your workflow

becominglit-dataset. Official download kit of the BecomingLit dataset from the NeurIPS 2025 paper: 'BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading'

GLM-Image. GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

ComfyUI-ReservedVRAM. A simple node that can dynamically adjust the reserved memory of a workflow in real-time, used to avoid the utilization of shared memory.

vision-pt. Python

SFD. [CVPR 2026] Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion

TwinFlow. [ICLR 2026] Taming large-scale few-step training with self-adversarial flows! 👏🏻

LongCat-Image. Python

PaDT. [ICLR 2026] Official implementation of "Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs"

iMontage. iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

jit_toy_example. Unofficial implementation of the toy example in JiT https://arxiv.org/abs/2511.13720

weave. Official Repo for Paper <WEAVE: Unleashing and Benchmarking the Interleaved Cross-modality Comprehension and Generation>

ComfyUI-piFlow. ComfyUI Nodes for AsymFlow and pi-Flow

toon. 🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.

ComfyUI-VAE-Utils. Python

ChronoEdit. [ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

EPG. [ICLR2026] There is No VAE: End-To-End Pixel-Space Generative Modeling Via Self-Supervised Pre-Training

Comfyui-QwenEditUtils. Python

VTC-Bench. [ACL2026 Main] Data & Code of "Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods"

Rex-Omni. [CVPR2026] Detect Anything via Next Point Prediction

Muon. Muon is an optimizer for hidden layers in neural networks

mammothmoda. Python

DeltaFlow. [NeurIPS'25 Spotlight] DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method

Cold-Diffusion-Models. Official implementation of Cold-Diffusion for different transformations in pytorch.

DiffusionNFT. [ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Qwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

RobusTok. Image Tokenizer Needs Post-Training

DIM. [ICLR 2026] Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

image-gs. Official implementation of SIGGRAPH 2025 paper "Image-GS: Content-Adaptive Image Representation via 2D Gaussians"

DepthAnythingAC. Official code for the paper: Depth Anything At Any Condition

ControlNet. Let us control diffusion models!

CRHD-3K. The first high-definition cloth retouching dataset CRHD-3K.

gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.

SiT. Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

MiniMax-Remover. This is the official implementation of our paper: "MiniMax-Remover: Taming Bad Noise Helps Video Object Removal"

OmniGen2. OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

LinGen. Python

asuka-misato. [CVPR 2025 Highlight] Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency

MeanFlow. PyTorch implementation of MeanFlow & iMF (one-step generative modeling).

YiXianMemo-python. YiXianMemo is a cards recording tool designed for Yi Xian: The Cultivation Card Game.

ObjectClear. [CVPR'26] ObjectClear: Precise Object and Effect Removal with Adaptive Target-Aware Attention

nanoDiT. Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.

ComfyUI-BrushNet. ComfyUI BrushNet nodes

Bagel. Open-source unified multimodal model

RORem. [CVPR2025] RORem: Training a Robust Object Remover with Human-in-the-Loop

DanceGRPO. An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

ZenCtrl. In-context subject-driven image generation while preserving foreground fidelity

Omnieraser. Python

T2I-R1. [NeurIPS 2025] T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Flow-Inference-Time-Scaling. [NeurIPS 2025] Official code for Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing

ICEdit. [NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!

xAR. This repository includes the official implementation of our paper "Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation"

Step1X-Edit. A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

ComfyUI-FramePackWrapper. Python

perception_models. State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

smart-card-workshop. An AI-powered content conversion tool that transforms text, web content, or HTML code into beautifully designed card images.一款基于AI的内容转换工具，可以将文本、网页内容或HTML代码转换为精美的卡片图像。

REPA-E. [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

ZoomEye. [EMNLP-2025 Oral] ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration

REPA. [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

FramePack. Lets make video diffusion practical!

Cobra. [SIGGRAPH 2025] Official code of the paper "Cobra: Efficient Line Art COlorization with BRoAder References". Cobra：利用更广泛参考图实现高效线稿上色

steplaw. Python

HiDream-E1. Python

DDT. [CVPR 2026] DDT: Decoupled Diffusion Transformer

VisualCloze. [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.)

CFG-Zero-star. Official repo for CFG-Zero*

RADIO. Official repository for "AM-RADIO: Reduce All Domains Into One"

MemeMeow. 智能检索张维为表情包

HiDream-I1. Python

PixWizard. [ICLR2025] A versatile image-to-image visual assistant, designed for image generation, manipulation, and translation based on free-from user instructions.

alphabet-dataset. Synthetic Alphabet Dataset

imm. Official implementation of Inductive Moment Matching

Edit-Transfer. Official code of "Edit Transfer: Learning Image Editing via Vision In-Context Relations"

OmniPaint. [ICCV 25] OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting

tiled_ksampler. Python

thera. [TMLR 2025] Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields

IterComp. [ICLR 2025] IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

tread. Python

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

fractalgen. PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

ml-gbc. Python

mdlm. [NeurIPS 2024] Simple and Effective Masked Diffusion Language Model

OmniParser. A simple screen parsing tool towards pure vision based GUI agent

Watermark-Removal-Pytorch. 🔥 CNN for Watermark Removal using Deep Image Prior with Pytorch 🔥.

hanzi-writer-data. The data used by Hanzi Writer

DiT-Extrapolation. Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

DeepEP. DeepEP: an efficient expert-parallel communication library

eqvae. [ICML'25] EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.

FlowEdit. Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

Diffusion-Sharpening. Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening

MaterialFusion. A framework for high-quality material transfer that allows users to adjust the degree of material application.

RAS. An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional variability in sampling steps

MakeAnything. Official code of "MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation"

FlashVideo. [AAAI-2026]FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

syncd. SynCD: Generating Multi-Image Synthetic Data for Text-to-Image Customization (ICCV 2025)

nodezator. A generalist Python node editor

ACE_plus. Python

TinyZero. Minimal reproduction of DeepSeek R1-Zero

ComfyUI-ColorshiftColor. Python

DiffusionLight. [CVPR 2024] code release for "DiffusionLight: Light Probes for Free by Painting a Chrome Ball"

LyCORIS. Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing. [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)

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

differential-diffusion. Python

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

dinov2. PyTorch code and models for the DINOv2 self-supervised learning method.

OneDiffusion. Official implementation of OneDiffusion paper (CVPR 2025)

Golden-Noise-for-Diffusion-Models. [ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".

ComfyUI-NPNet. https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUI

ComfyUI_mistral_api. A ComfyUI custom node that integrates Mistral AI's Pixtral Large vision model, enabling powerful multimodal AI capabilities within ComfyUI. Pixtral Large is a 124B parameter model (123B decoder + 1B vision encoder) that can analyze up to 30 high-resolution images simultaneously.

ComfyUI_AdvancedRefluxControl. Python

Comfyui-In-Context-Lora-Utils. Python

qwen2vl-flux. Python

OminiControl. [ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer

Subjects200K. Subjects200K dataset

ComfyUI-APQNodes. useful custom nodes for ComfyUI

Comfyui_Object_Migration. This is a study aim to transfer the single concept by using DIT model self-attention capablity

In-Context-LoRA. Official repository of In-Context LoRA for Diffusion Transformers

HiDiffusion. [ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!

FiT. [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model

ComfyUI-Fluxtapoz. Nodes for image juxtaposition for Flux in ComfyUI

text-clustering. Easily embed, cluster and semantically label text datasets

T2ITrainer. Practice Code for text to image trainer

OmniGen. OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

Eagle. Eagle: Frontier Vision-Language Models with Data-Centric Strategies

MPS. Python

SPRIGHT. [ECCV 2024] Official PyTorch implementation of "Getting it Right: Improving Spatial Consistency in Text-to-Image Models"

flux. Official inference repo for FLUX.1 models

rectified-flow. 从零手搓Flow Matching（Rectified Flow）

CoMat. [NeurIPS 2024] 💫CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching

bilibili-api.

ViPer. Python

data-juicer. Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

ComfyUI-Kolors-MZ. Kolors的ComfyUI原生采样器实现(Kolors ComfyUI Native Sampler Implementation)

ComfyUI-KwaiKolorsWrapper. Diffusers wrapper to run Kwai-Kolors model

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Kolors. Kolors Team

PhiCookBook. This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks

HunyuanDiT. Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

TroL. [EMNLP 2024] Official PyTorch implementation code for realizing the technical part of Traversal of Layers (TroL) presenting new propagation operation to get super vision language performances.

Lumina-T2X. Lumina-T2X is a unified framework for Text to Any Modality Generation

ComfyUI-LuminaWrapper. Python

SD-Latent-Interposer. A small neural network to provide interoperability between the latents generated by the different Stable Diffusion models.

Inf-DiT. Official implementation of Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer

modern_ai_for_beginners. modern AI for beginners

Long-CLIP. Scripts for use with LongCLIP, including fine-tuning Long-CLIP

Perturbed-Attention-Guidance. Official implementation of "Perturbed-Attention Guidance"

InternLM-XComposer. InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

compel. A prompting enhancement library for transformers-type text embedding systems

PixArt-sigma. PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

schedule_free. Schedule-Free Optimization in PyTorch

LaVi-Bridge. [ECCV 2024] Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation

ComfyUI-layerdiffuse. Layer Diffuse custom nodes

sd-forge-layerdiffuse. [WIP] Layer Diffusion for WebUI (via Forge)

Neural-Network-Diffusion. We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

imgutils. A convenient and user-friendly anime-style image data processing library that integrates various advanced anime-style image processing models

waifuc. Efficient Train Data Collector for Anime Waifu

PickScore. Python

PIA. [CVPR 2024] PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA，你的个性化图像动画生成器，利用文本提示将图像变为奇妙的动画

sliders. Concept Sliders for Precise Control of Diffusion Models

ComfyUI_ExtraModels. Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.

ComfyUI-EasyNode. JavaScript

onediff. OneDiff: An out-of-the-box acceleration library for diffusion models.

PoolNet. Code for our CVPR 2019 paper "A Simple Pooling-Based Design for Real-Time Salient Object Detection"

consistencydecoder. Consistency Distilled Diff VAE

Awesome-Aesthetic-Evaluation-and-Cropping.

PixArt-alpha. PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

generative-models. Generative Models by Stability AI

pdfmake. Client/server side PDF printing in pure JavaScript

vue-content-loader. SVG component to create placeholder loading, like Facebook cards loading.

vue-api-query. 💎 Elegant and simple way to build requests for REST API