What Is Enhancer?
Krea Enhancer is an AI-powered upscaling and refinement tool for images and videos. It is designed to improve resolution, recover lost detail, and sharpen clarity — whether you are working with an existing asset or an image previously generated in Krea.
Common use cases include blowing up a low-resolution archive image for print, sharpening a photograph that is blurry or underexposed, or bringing a low-resolution AI output up to a quality suitable for larger formats.
Use the Edit tool for making major changes to the style or appearance of an image. Enhancer uses AI to reconstruct what a sharper, higher-resolution version of an image might look like — it does not recover what was originally there. It cannot reveal what text on a blurry sign actually said, for example. Enhancer is a creative tool, not a forensic one.
When to Use Enhancer
| Situation | Notes |
|---|
| Blown-out or underexposed photographs | AI fills in lost highlight or shadow detail |
| Motion blur or slow shutter speed | Recovers perceived sharpness |
| Zooming into a small area without pixellation | Use 2x or 4x upscaling |
| Out-of-focus elements | Use with Face Detection for portraits |
| Low-resolution or heavily compressed source images | Any model works well here |
| AI-generated images needing higher resolution | For example, upscaling a 1024px output to 4K for print |
| Low-quality digital renders | Topaz Generative adds fine texture and detail |
Getting Started
1. Upload or select an image
Upload the image you want to enhance, or select one from your previous Krea generations. The left sidebar gives quick access to previous enhancement jobs.
2. Choose an enhancement model
The model selector is at the bottom left of the page. Choose your model before adjusting any settings, as each model exposes a different set of controls. See the model comparison table at the end of this page for guidance on which to use.
3. Set an upscale factor
Four scaling options are available: 1x, 2x, 4x, and 8x.
Use 1x if the original image has adequate resolution but needs sharpening or clarity improvements. Choose a higher multiplier to increase the output dimensions at the same time. Note that higher upscale values give the AI more room to interpret and fill in detail, which can introduce subtle modifications to textures and edges.
4. Adjust the settings
Available settings vary by model. The table below describes each one.
| Setting | Model | Description |
|---|
| Strength | Krea Enhance | Controls how much additional detail the AI invents. Higher values produce sharper results with more AI interpretation. |
| Resemblance | Krea Enhance | Higher values keep the output closer to the original image. Lower values allow more variation. |
| Clarity | Krea Enhance | Higher values push the output toward the supplied prompt. |
| Sharpness | Krea Enhance, Upscale V1 | Increases output sharpness. This is closer to a traditional image setting than an AI one. |
| Match color | Krea Enhance | When enabled, the output color palette matches the source image precisely. |
| Denoise | Topaz, all models | Reduces film grain, sensor noise, and compression artifacts. |
| Model | Topaz | Selects the Topaz sub-model: Standard, Low Resolution, High Fidelity, or CGI. |
| Face detection | Topaz, all models | Enables face-aware enhancement. Unlocks Face Creativity and Face Strength settings. |
| Face creativity | Topaz, all models | Controls how much the AI reconstructs unclear or blurry facial features. |
| Face strength | Topaz, all models | Controls the intensity of the face enhancement effect. |
| Creativity | Topaz Generative | Similar to Strength — increases generative detail and AI interpretation. |
| Texture | Topaz Generative | Controls fine-detail density. A lower value upscales existing detail; a higher value generates additional texture — extra brushstrokes in a painting, more blades of grass in a landscape. |
5. Add a prompt (optional)
A prompt describes the final image you want to see and helps the AI make decisions about how to fill in missing detail. This is particularly useful when the source image is ambiguous — for example, a silhouetted figure where the clothing and appearance are unclear.
Describe the final image you want to see, not the change you want made. Write “a bright daylight scene” rather than “change the scene from night to day.”
6. Scene Transfer (Krea Legacy only)
Scene Transfer allows you to modify the lighting, environment, and mood of an image. Upload a reference scene or enter a text-based scene description to guide the transformation. For example, applying a “cinematic blue lighting” description can shift an image toward a high-contrast, film-inspired look.
7. Run the enhancement
Click Enhance to start processing. Generation time ranges from roughly 10 to 120 seconds depending on the model and upscale factor selected.
Once complete, drag the comparison slider to view before and after versions side by side, or use the view controller at the bottom right to switch between layouts. Your result appears as a thumbnail at the bottom of the screen and is also saved to Assets. You can run multiple enhancements of the same image with different settings — each result saves as a separate thumbnail so you can compare them directly. Multiple enhancement jobs can also run simultaneously.
Enhancement Presets (Krea Legacy)
In the Krea Legacy model, presets adjust the settings sliders automatically to target a particular aesthetic.
| Preset | Description |
|---|
| Default | Balanced sharpness and clarity with standard AI refinement |
| Flat Sharp | Enhances texture and sharpness without altering color grading |
| Strong | Increases contrast and detail intensity |
| Reinterpretation | Allows the AI to creatively reimagine the composition while improving resolution |
| Oil Painting | Softens edges and adjusts textures for a painterly effect |
| Digital Art | Produces a stylized, high-fidelity digital look |
Image Enhancement Models
| Model | Description | Speed | Maximum resolution |
|---|
| Krea Enhance | Generative upscaler suited for adding detail and improving lower-resolution AI images | 30s | 8K |
| Upscale V1 | Fast, neutral upscaler that preserves existing detail well | 5s | 8K |
| Bloom | Creative upscaler that adds detail faithfully to the original image, up to 8K | 60s | 10K |
| Topaz | Powerful upscaler with advanced controls | 10s | 22K |
| Topaz Generative | More AI-forward version of Topaz, with creative texture generation | 40s | 16K |
| Krea Legacy | Original enhancement model, includes Scene Transfer | 30s | 4K |
A note on upscale dimensions
The upscale factor refers to the increase in width and height, not total file size. Because image dimensions scale in two directions, the overall size of the image grows as follows:
| Upscale factor | Output image size relative to original |
|---|
| 1x | 1x |
| 2x | 4x |
| 4x | 16x |
| 8x | 64x |
Enhancing Videos
Video enhancement uses the same general interface as image enhancement, but with a different set of models and settings. Be aware that video upscaling can consume your compute budget quickly, particularly at higher resolutions or with frame interpolation enabled.
Upscaling videos can consume your compute budget quickly.
Video upscaling settings
| Setting | Options | Description |
|---|
| Resolution | Up to 8K (model dependent) | Output resolution. Defaults to your source dimensions. |
| Enhancement | On/Off | Master toggle for AI enhancement processing. |
| Video type | Progressive, Interlaced, Progressive & Interlaced | Source footage format. Most modern digital video is progressive. |
| Model | Proteus, Iris, Artemis, Nyx, Gaia, Apollo | Topaz sub-model selection. See the comparison table below. |
| Focus fix | None, Normal, Strong | Attempts to correct out-of-focus elements in the source footage. |
| Parameters | Auto, Manual | Auto is recommended for most users. Manual exposes controls for compression artifact reduction, detail recovery, pre-blur, sharpening, noise reduction, and halo minimization. |
| Creativity | Low, High | Controls the AI’s interpretive range. Low is conservative; High applies more aggressive enhancement. |
Frame interpolation settings
Frame interpolation generates new frames between existing ones to increase frame rate or create slow-motion effects.
| Setting | Options | Description |
|---|
| Frame interpolation | On/Off | Enables frame generation. |
| Frame rate | 30, 60, 90, 120 fps | Target frame rate for the output video. |
| Model | Apollo | Primary model for frame interpolation and slow-motion. |
| Slow motion | 1x to 8x | Slow-motion multiplier. A value of 3x produces footage three times slower than the source. |
| Fix duplicate frames | On/Off | Detects and replaces duplicate frames with interpolated ones. |
| Sensitivity | 0-100% | Controls how aggressively the model responds to motion. Default is 9%. |
Grain settings
| Setting | Options | Description |
|---|
| Grain | On/Off | Adds a film grain effect for a natural or cinematic look. |
| Strength | 0.0 - 0.1 | Grain intensity. Default is 0.02, which is very subtle. |
| Size | 0.1 - 5.0 | Grain particle size. Default is 1.0. Smaller values produce finer grain. |
Krea Video settings
| Setting | Options | Description |
|---|
| Upscaling level | 1x, Max | Use 1x to preserve the source dimensions, or Max to increase to 4096x2160. |
| Frame rate | 30, 60, 120 fps | Target frame rate for the output. |
| Prompt | Text | Describe the video content to help the AI process the footage accurately. |
| AI strength | 0-100% | Controls how strongly the AI adjusts the footage toward the prompt. Default is 39%. |
| Resemblance | 0-100% | Controls how closely the output matches the source. Default is 48%. Higher values stay closer to the original. |
| Preset | Cinematic, Render, Animation | Pre-configured settings optimized for different video types. |
| Looped | On/Off | Enable if the output should loop seamlessly, with matching first and last frames. |
Topaz sub-models compared
| Model | Best for | Strengths | Limitations |
|---|
| Proteus | General upscaling | Versatile default with manual controls for compression, detail, and sharpening | Can produce softer textures compared to specialized models |
| Iris | Face enhancement | Better facial clarity and sharpness than Proteus on low to medium quality video | Can introduce warping or distortion on close-up zooms |
| Artemis | Denoising | Good denoising with more retained sharpness than Nyx | Less smoothing than Nyx; may leave residual noise |
| Nyx | Denoising, archival footage | Effective at removing noise and grain, particularly in older footage | Aggressive smoothing can reduce fine detail and realism |
| Gaia | High-quality sources, animation | Well suited for upscaling 1080p or higher inputs and extracting animation detail | Less effective on lower-quality source footage |
| Apollo | Slow motion | Produces smooth 4x and 8x slow-motion effects | Intended specifically for slow-motion and frame interpolation |
