ComfyUI and ComfyUI_UltimateSDUpscale
About ComfyUI
Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Supports diverse generative models across image, video, audio, and 3D modalities with intelligent memory management and GPU offloading for low-VRAM systems. The architecture uses an asynchronous queue system with incremental execution—only re-computing workflow nodes that have changed—and integrates LoRAs, ControlNets, and model merging capabilities. Extensible through custom nodes and external API providers, while maintaining fully offline operation for core functionality.
About ComfyUI_UltimateSDUpscale
ssitu/ComfyUI_UltimateSDUpscale
ComfyUI nodes for the Ultimate Stable Diffusion Upscale script by Coyote-A.
Implements tiled image-to-image diffusion processing that breaks large images into smaller patches for upscaling, preserving fine details while reducing VRAM requirements and respecting the diffusion model's native resolution training bounds. Integrates directly into ComfyUI's node system as custom `image/upscaling` nodes with configurable tiling and blending parameters. Ports the established Ultimate Upscale algorithm from the Automatic1111 WebUI to ComfyUI's modular node architecture.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work