Upscale model
4x-UltraSharp. safetensors
4x UltraSharp · Upscale model for ComfyUI
- File
4x-UltraSharp.safetensors- Type
- Upscale model
- Size
- 66.9 MB
- Folder
ComfyUI/models/upscale_models/- Source
- Kim2091/UltraSharp
- SHA-256
36a340b5509b…
2 workflows use this file
What is 4x UltraSharp?
4x UltraSharp is an upscale model that increases image resolution while preserving or enhancing detail. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect 4x UltraSharp with other models and custom nodes to build any pipeline you need. There are 2 official ComfyUI workflow templates that use 4x UltraSharp, ready to load and customize.
Workflows for this file
- Wan2.2, Z-Image-Turbo
AIrt MAchIne
Uses this file - Wan, Wan2.2
Wan 2.2 14B Image to Video
- Wan2.2, Wan
Wan 2.2 5B Video Generation
- Wan2.2, Wan
Wan 2.2 14B Text to Video
- Wan2.2, Wan
Wan 2.2 14B First-Last Frame to Video
- Wan2.2, Wan
Wan2.2-S2V Audio-Driven Video Generation
- Wan2.2, Wan
Wan 2.2 14B Fun Control
- Wan2.2
Multi-Keyframe Video Stitching
Frequently Asked Questions
4x UltraSharp is an upscale model that increases image resolution while preserving or enhancing detail. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect 4x UltraSharp with other models and custom nodes to build any pipeline you need. There are 2 official ComfyUI workflow templates that use 4x UltraSharp, ready to load and customize.
Open ComfyUI and browse any of the 2 official ComfyUI workflow templates that use 4x UltraSharp. Load one as a starting point, then customize the nodes and parameters to fit your use case.
There are 2 official ComfyUI workflow templates that use 4x UltraSharp. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. 4x UltraSharp weights are available to download from Hugging Face. You only pay for compute when running on Comfy Cloud; local inference on your own hardware is always free.