Native Multimodal Models are World Learners

A simple mod to ComfyUI that adds a Workflow to Workflow "API" converter endpoint

Code for MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency

A powerful set of tools for ComfyUI

This workflow experiments with image detailing using a mix of techniques like latent space manipulation and interpolation. I've been playing around with multiple passes to enhance detail while tryi…

ComfyUI-QwenVL custom node integrates the Qwen-VL series, including the latest Qwen3-VL models, including Qwen2.5-VL and the latest Qwen3-VL, to enable advanced multimodal AI for text generation, i…

ComfyUI ShadowR Wrapper

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Texturing tool for projecting images from multiple cameras to one UV Map.

Model Compression Toolbox for Large Language Models and Diffusion Models

A minimal implementation of DeepMind's Genie world model

Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

Divide and Conquer Node Suite

Awesome curated collection of images and prompts generated by gemini-2.5-flash-image (aka Nano Banana) state-of-the-art image generation and editing model. Explore AI generated visuals created with…

IntrinsiX: High-Quality PBR Generation using Image Priors

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

[CVPR2025] MAGE : Single Image to Material-Aware 3D via the Multi-View G-Buffer Estimation Model

PlayerOne: Egocentric World Simulator

Wan: Open and Advanced Large-Scale Video Generative Models

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

ComfyUI Depth Anything (v1/v2/distill-any-depth) Tensorrt Custom Node (up to 14x faster)

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

[NeurIPS 2025] The official repository of "Sekai: A Video Dataset towards World Exploration"

A Unified and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for 🤗Diffusers.

[ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos

Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition