Skip to main content
This guide covers image upscaling workflows in ComfyUI, including local models and partner node options for various use cases.
For a comprehensive deep-dive with benchmarks and visual comparisons, see The Complete AI Upscaling Handbook on the ComfyUI Blog.

Key concepts

Upscaling vs. enhancement

  • Upscaling increases resolution while reconstructing detail.
  • Enhancement improves perceived quality (denoise, sharpen, restore, color, faces, etc.).
The best practice in AI pipelines usually combines both steps.

Creative vs. conservative upscale

ConservativeCreative
ApproachPreserve the originalReimagine and enhance
StrengthsHigh accuracy, consistency, production-safeRich details, sharper, more visually striking
LimitsCan appear flat, limited improvement on poor inputPossible hallucinations or structural drift
ModelsMagnific Precise, SeedVR2, FlashVSR, Topaz Fast, HitPawWan 2.2, Magnific Creative, Topaz Astra, HitPaw Creative

Use cases

Portrait and skin enhancement

Achieving realistic skin details while maintaining character consistency is key for portrait upscaling. The best models add texture, pores, and natural skin imperfections. In this domain, Magnific Image Skin Enhancer far outperforms the rest. Recommended: Magnific Image Skin Enhancer

Product photography

Maintaining faithful representation of materials, product label edges, and small text requires conservative upscaling models. Recommended: HitPaw, Magnific Precise, WaveSpeed SeedVR2, Nano Banana Pro

Landscape and environments

The model choice depends on your needs:
  • Creative models: Make environmental shots pop with details and mood.
  • Conservative models: Keep buildings and structures consistent.
Creative models may reimagine artifacts while conservative models will not. Any model can potentially fit your needs depending on your specific requirements.

Stylized art and illustration

For distinct or unique styles, conservative models work best to avoid adding unwanted details. For images with room for detail, creative models can improve the style. Recommended: Magnific Creative, Topaz Image Enhance, Nano Banana Pro Tip: Adjust the creativity parameters in Magnific Creative and Topaz Image Enhance to find the right balance. Nano Banana Pro can also work well for more common styles and adding details.

AI-generated images

When it comes to upscaling images that have typical AI issues such as too many fingers, artifacts, incorrect anatomy, and morphing, the assumption is that creative upscales can fix it. Sometimes that’s true, but other times not so much. Best practice is to resolve these issues prior to upscaling with image-edit models or traditional tools (or generate a new image entirely).

Available models

Local models (ESRGAN)

For basic local upscaling using ESRGAN models, see the basic upscale tutorial.
ModelBest for
RealESRGANGeneral-purpose upscaling
BSRGANText and sharp edges
SwinIRNatural textures, landscapes

General creative upscaling

For general creative upscaling across various use cases:

Partner nodes

Partner nodes provide access to advanced upscaling models via API.
ModelTypeMax resolutionFeatures
Topaz Image Enhance (Bloom)Creative8KSubject detection, face enhancement, color preservation
Magnific PreciseConservative-High accuracy, production-safe
Magnific CreativeCreative-Detail reimagination, skin enhancement
Magnific Skin EnhancerCreative-Portrait-specific, adds realistic skin texture
Nano Banana ProConservative-Fast, good for product photography
WaveSpeed SeedVR2Conservative-High fidelity
HitPawBoth-Conservative and creative modes

Benchmark: 1K to 4K upscale time

ModelTime
Nano Banana Pro~80s
Topaz Image Enhance~100s

Tips

  • For SeedVR2, downscale the image to 0.35 megapixels with the ImageScaleToTotalPixels node before upscaling for better results.
  • Chain multiple upscale nodes (e.g., 2x → 4x) for ultra-high magnification.
  • Connect upscale nodes after generation for “generate + enhance” pipelines.
  • Test multiple models on your specific image type to find the best fit.