AI Lab
How to access: Click the AI Lab icon in the top-left corner of the Edit interface.
In the current UI, AI Lab is grouped by capability type. The main sections are Background & Scene, Remove & Repair, Subject Adjustments, and Enhance & Restore. Depending on the editing task, related portrait, background, and color panels may also show recommendation cards or search suggestions that help you find relevant AI Lab tools more quickly.
- Background & Scene: Tools for replacing or rebuilding the visual scene around the subject.
- Remove & Repair: Tools for removing distractions and repairing unwanted people or objects.
- Subject Adjustments: Tools for targeted subject refinements.
- Enhance & Restore: Tools for recovering, restoring, and improving image quality.
Batch Edit
Use Batch Edit to process multiple photos from AI Lab without entering each tool one by one. Select the photos you want to process, choose the AI effects to apply, and click Start to generate results in one workflow.
Batch Edit currently supports People Removal, Old Photo Restoration, and Detail Enhance.
Background & Scene
AI Background Fusion
AI Background Fusion helps you create more complete and atmospheric scene-based portraits through intelligent cutout, background replacement, and layered foreground composition.
Batch Scene Workflow
AI Background Fusion supports saving a complete scene setup as a custom preset, including the background, foreground, subject placement, and crop. You can apply the same scene setup to selected photos and generate the final results in batches.
- Import a batch of photos into AI Lab > AI Background Fusion.
- Choose one photo, complete the scene edit, and save the result as a preset.
- Switch to Grid View to review multiple composites.
- Select the photos you want to process and use Batch Apply to apply the saved scene setup.
- Make any needed adjustments, then click Batch Generate.
- Click Save All at the bottom of the left panel to save the generated results.
Feature details
- Automatically cuts out the subject, with manual brush refinement available when needed.
- Supports both Subject Only and Subject + Connected Objects recognition modes.
- Lets you choose from official scene packs or upload custom backgrounds.
- Supports layered foreground assets for additional composition control, including foreground order adjustment.
- Allows repositioning, scaling, rotation, and horizontal / vertical flipping of the subject.
- After generation, Character Lighting can be used to improve the visual blend between the subject and the background.
Asset and upload limits
- Official packs can be filtered by scenarios such as General, Student, Sports, Children, Infant, Outdoor, and Indoor.
- Supports up to 50 foreground elements in one composition.
- Custom backgrounds support JPG / PNG / WebP; custom foregrounds currently support PNG only.
- Custom uploaded assets are limited to a maximum long side of 4000 px and 20 MB per file.
Notes
- Generated results appear in the Results list and can be saved individually or in batches.
- Saved results return to the gallery as new images.
- Unsaved AI Background Fusion results are lost when leaving the feature.
- Generation requires a background on the canvas, and the subject must remain within the visible canvas area.
Remove & Repair
Smart Removal
Removal Mode
- Magic Removal: Best suited for removing large or complex distractions and for producing more natural-looking results. 0.5 credits are used per application.
- Quick Removal: Best suited for removing smaller distractions with faster processing. 0.1 credits are used per application.
- Manual Tuning: Paint directly over areas to add or remove mask regions. Brush size and softness can be adjusted.
Supporting Tools
- Subject Protection: Protects detected subjects or associated items, with brushing limited to areas outside the subject.
- Edge Optimization: Automatically refines the transition edges around the subject.
Apply Effect: Click Remove to apply the effect. Each application uses the corresponding credits.
People removal
Passerby Selection
- Auto Detection: The system automatically identifies passerby areas. Click again to re-detect the mask. After auto detection, the manual brush can be used to refine the result.
- Manual Tuning: Paint over passerby areas to add or remove mask regions. Brush size, softness, and opacity are adjustable.
Apply Effect: Click Continue > Generate to apply the effect. Each application uses 0.3 credits.
Save Options
Choose how you would like the effects to be applied after using AI Lab (People removal / Smart Removal) and returning to the Edit interface.
- Apply to Current Image (Keep one image copy): The effect is applied directly to the current photo in the editing interface. The original source file is not modified.
- Generate Copy (Create a new copy): A new copy with the applied effect is created. You can change the storage location for generated copies in Settings.
Strong Glare Removal
Use AI Lab > Remove & Repair > Strong Glare Removal to remove large glasses glare or bright lens reflections that regular glass glare removal may not fully cover.
- For group photos, select the person you want to process before generating the AI Lab result.
- After the result is generated, review it and save the version you want to keep.
- If a photo has already been imported with regular glass glare removal applied, AI Lab continues from that edited result and may not detect the original glare.
Subject Adjustments
Belly Slimming
Use AI Lab > Belly Slimming to refine the waist and abdomen area with one click for a cleaner body silhouette.
- How to use: Click Generate, review the result in Results, and save it when you are satisfied.
- Suitable scenarios: Wedding, gown, portrait, and travel photos where the abdominal outline needs refinement.
Notes
- Some images may show weaker slimming, reduced clothing texture, visible skin texture changes on uncovered areas, or occasional unnatural abdominal definition.
Enhance & Restore
Old photo restoration
Use AI Lab > Old photo restoration to repair old photos, enhance details, and optionally add natural color to black-and-white photos.
- How to use: Click Generate, compare the results in Results, and save the version you prefer.
- Default behavior: Colorization is enabled by default.
- Output: Supports standard 2K and 4K output.
- Suitable scenarios: Yellowed, faded, scratched, damaged, or blurry old photos.
Notes
- If faces are very small or the source image is extremely blurry, the model may redraw facial details. In some cases, accessories such as glasses or necklaces may also be affected.
Detail Enhance
Use AI Lab > Detail Enhance to improve image sharpness, texture, and fine details such as hair, facial details, and clothing patterns. Detail Enhance can also export higher-resolution results when the source image and final delivery needs require it.
Resolution options
- No Upscale: keeps the original image size and focuses on clarity enhancement. This is useful when the source image is already high resolution and only needs detail recovery.
- 2K, 4K, and 6K: enlarge the output to the selected resolution while enhancing detail. These options are useful for low-resolution sources, larger delivery sizes, or images that need more room for cropping.
When you enter AI Lab after cropping, available resolution options may depend on the current image size.
Notes
- Results may be limited on noisy, heavily blurred, or very low-resolution images.
- Very high-resolution images may show limited improvement or slight local consistency issues.
- Fine facial texture can look less natural if the source quality is too low or the upscale amount is too aggressive.
