Video to Video with Camera Control with Wan

ComfyUI-Custom-Scripts

ComfyUI-Custom-Scripts enhances COMFYUI with features like autocomplete for embeddings, auto-arranging graphs, and custom node functionalities, improving user experience and workflow efficiency.

dspy_nodes

DSPy Nodes for COMFYUI facilitates the development of DSPy pipelines, enhancing visibility and iteration in program structure while integrating key DSPy features within the COMFYUI environment.

ComfyUI-xzuynodes

This repository offers a set of custom nodes for COMFYUI, enhancing video frame extraction and image resizing, while improving CLIP model loading for better GPU performance.

ComfyUI_Swwan

The ComfyUI LayerStyle Utility Nodes enhance image processing in the COMFYUI environment, offering features like smart cropping, aspect ratio scaling, and image restoration for streamlined workflows.

ComfyUI_crdong

ComfyUI_crdong is a tool designed to enhance the functionality of COMFYUI's Stable Diffusion WebUI, offering unique features that improve user experience and output quality in creative workflows.

ComfyUI-Florence2

Florence2 for COMFYUI enhances vision tasks through a prompt-based model, featuring Document Visual Question Answering (DocVQA) for extracting information from document images, improving user interaction and output quality.

ComfyUI-WanVideoWrapper

This COMFYUI extension enhances video generation by optimizing VRAM usage and improving LoRA weight management, enabling efficient model integration and exploration of new features without compatibility issues.

ComfyUI-Dynamic-Lora-Scheduler

The Adaptive LoRA Scheduler for COMFYUI enables dynamic blending of multiple LoRAs based on input image complexity. Its features include customizable blending curves and real-time visual previews, enhancing image generation workflows.

ComfyUI-VideoHelperSuite

The ComfyUI-VideoHelperSuite enhances video workflows within COMFYUI by providing nodes for loading videos and images, combining them into videos, and managing audio, all with customizable settings for frame rates and formats.

ComfyUI Official

ComfyUI is a versatile graphical interface for building and managing complex Stable Diffusion workflows, utilizing a node-based system for enhanced user experience and flexibility.

wlsh_nodes

WLSH ComfyUI Nodes enhance COMFYUI by introducing custom nodes for metadata manipulation, latent image generation, and advanced sampling, streamlining workflows and improving user experience within the Stable Diffusion framework.

ComfyUI-GGUF-FantasyTalking

This repository is currently non-functional due to issues with quantizing the fantasy talking model, limiting its integration within COMFYUI's ecosystem.

ComfyUI-KJNodes

KJNodes for COMFYUI offers custom nodes enhancing user experience by streamlining workflows, such as color masking, condition combining, and real-time status updates, improving efficiency in Stable Diffusion tasks.

ComfyUI_LayerStyle

ComfyUI Layer Style offers a collection of nodes that enable Photoshop-like layer compositing and masking functionalities within COMFYUI. It aims to centralize workflows and reduce software switching. Key features include: - **Layer Compositing**: Users can blend multiple images with various blending modes, enhancing creative flexibility. - **Masking Tools**: Advanced masking options allow for precise control over image areas, including feathering and edge refinement. - **Image Processing**: Functions like color adjustments, noise addition, and detail restoration improve overall image quality. These tools enhance user experience by streamlining the creative process and improving output quality. Acknowledgments go to the original authors of the underlying code and models.