Upscaling Images
Fater includes specialized AI models designed to upscale your images, meaning they increase the image's resolution (pixel dimensions) while intelligently enhancing details and attempting to maintain or improve overall quality. This is invaluable for preparing images for high-resolution displays, print, or simply to recover detail from smaller source images.
Upscaling is typically done in the Image Editor.
When to Use AI Upscaling
Increasing the resolution of existing renders, photographs, or AI-generated images.
Adding sharpness and clarity to slightly blurry or soft images.
Revealing finer details that might be lost in lower-resolution versions.
Preparing images for large-format printing or display.
Workflow for Upscaling Images
Prepare Your Image Layer & Generation Area:
Ensure the image content you want to upscale is visible within the Generation Area Bounding Box on your Inpaint Canvas. The AI will process the content within this box.
Mask (Optional - for Selective Upscaling): If you only want to upscale a part of an image, create a Mask over that area.
Select an Upscaling AI Model:
Go to the Model Selector (Left Sidebar), choose the "Upscale" category (🖼️ icon), and select a model.
Configure Upscaling Parameters:
Adjust settings in the Left Sidebar. Key parameters include:
Prompt & Negative Prompt: Can sometimes refine upscale style.
Scale Factor & Output Megapixels (Resolution Control):
Scale: A direct multiplier for the input dimensions (e.g., 2x, 4x).
Output Megapixels: Allows you to target a specific final resolution in millions of pixels.
How they interact: Fater determines the AI model's internal processing size based on a combination of:
The current dimensions of your Generation Area Bounding Box (this is the "input image" for the upscaler).
The chosen Scale factor.
The target Output MegaPixels. The system intelligently calculates the optimal internal dimensions for the model to achieve an output that respects both your desired scale and target megapixel count as closely as possible. This means you don't usually need to precisely calculate input sizes yourself; set your desired final output characteristics.
Creativity / Resemblance: Balance new detail vs. faithfulness to the original.
Sharpen, Dynamic, Tile Size, More Details, Hand Fix, Checkpoint: Further refine the process.
Mask Alpha Radius (for masked upscaling): Controls edge blending if a mask is used.
(See Understanding Generation Parameters and the AI Models for details).
Initiate Upscaling:
Click the Generate button (✨) in the Floating Prompt Area.
Review and Use Results:
The first upscaled image is automatically added as a new layer.
Other variations (if any) appear in the Generation Task List.
Example Scenario : Preparing a Product Shot for a Large Banner
Image Layer: You have a good but medium-resolution product photo on a layer.
Generation Area: Set the bounding box to cover the entire product photo.
Model: Select "High [Upscale]".
Parameters:
Set Scale to 4x and Output Megapixels to your target banner resolution.
Generate.
Review the new high-resolution layer.
AI Upscaling in Fater can significantly enhance the quality and usability of your images, making them suitable for a wider range of applications.
Last updated