Stars
ComfyUI custom node for NVIDIA PiD pixel diffusion decoding and upscale workflows
LTX Director and a variety of other custom ComfyUI nodes and workflows
A ComfyUI custom node suite for Qwen3-TTS, supporting 1.7B and 0.6B models, Custom Voice, Voice Design, Voice Cloning and Fine-Tuning.
Nodes related to video workflows
All-in-one Flux2 text-to-image & image editing node that combines CLIP encoding, VAE encoding, and reference latent injection.
An image gallery node that displays previews for easy selection.
A ComfyUI node that adds random noise to text embeddings.
Compositor Node experiments
A collection of ComfyUI custom nodes.- Awesome smart way to work with nodes!
The nodes detached from [ComfyUI Layer Style](https://github.com/chflame163/ComfyUI_LayerStyle) are mainly those with complex requirements for dependency packages.
GGUF Quantization support for native ComfyUI models
Tiled Diffusion, MultiDiffusion, Mixture of Diffusers, and optimized VAE
A simple sidebar for your ConfyUI!
ComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL and the latest Qwen3-VL, with GGUF support for advanced multimodal AI in text generation, image understanding, and vi…
ComfyUI DyPE, enabling artifact-free 4K+ image generation for Qwen, Flux + Nunchacku
Wrapper of DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion, run in diffusers mode
Workflow-to-APP、ScreenShare&FloatingVideo、GPT & 3D、SpeechRecognition&TTS
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
[CVPR 2025 Highlight🌟] Official ComfyUI implementation of "HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis"
Lets make video diffusion practical!
JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.
Official repository of In-Context LoRA for Diffusion Transformers