Key concepts
Upscaling vs. enhancement
- Upscaling increases resolution while reconstructing detail.
- Enhancement improves perceived quality (denoise, sharpen, restore, color, faces, etc.).
Creative vs. conservative upscale
| Conservative | Creative | |
|---|---|---|
| Approach | Preserve the original | Reimagine and enhance |
| Strengths | High accuracy, consistency, production-safe | Rich details, sharper, more visually striking |
| Limits | Can appear flat, limited improvement on poor input | Possible hallucinations or structural drift |
| Models | Magnific Precise, SeedVR2, FlashVSR, Topaz Fast, HitPaw | Wan 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 EnhancerProduct photography
Maintaining faithful representation of materials, product label edges, and small text requires conservative upscaling models. Recommended: HitPaw, Magnific Precise, WaveSpeed SeedVR2, Nano Banana ProHitPaw
Try on Comfy Cloud
Nano Banana Pro Product
Try on Comfy Cloud
SeedVR2 (Open Source)
Try on Comfy Cloud
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.
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 thecreativity 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.| Model | Best for |
|---|---|
| RealESRGAN | General-purpose upscaling |
| BSRGAN | Text and sharp edges |
| SwinIR | Natural textures, landscapes |
General creative upscaling
For general creative upscaling across various use cases:Topaz Creative
Try on Comfy Cloud
HitPaw Creative
Try on Comfy Cloud
Recraft Creative
Try on Comfy Cloud
Recraft Crisp
Try on Comfy Cloud
Nano Banana Pro Portrait
Try on Comfy Cloud
Partner nodes
Partner nodes provide access to advanced upscaling models via API.| Model | Type | Max resolution | Features |
|---|---|---|---|
| Topaz Image Enhance (Bloom) | Creative | 8K | Subject detection, face enhancement, color preservation |
| Magnific Precise | Conservative | - | High accuracy, production-safe |
| Magnific Creative | Creative | - | Detail reimagination, skin enhancement |
| Magnific Skin Enhancer | Creative | - | Portrait-specific, adds realistic skin texture |
| Nano Banana Pro | Conservative | - | Fast, good for product photography |
| WaveSpeed SeedVR2 | Conservative | - | High fidelity |
| HitPaw | Both | - | Conservative and creative modes |
Benchmark: 1K to 4K upscale time
| Model | Time |
|---|---|
| Nano Banana Pro | ~80s |
| Topaz Image Enhance | ~100s |
Tips
- For SeedVR2, downscale the image to 0.35 megapixels with the
ImageScaleToTotalPixelsnode 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.