Skip to main content
This guide shows how to run the Bria Image Editing workflows in ComfyUI. For what the models are and what they do best, see the Bria Image Editing overview. Each workflow takes a single input image plus a mask. The Painter node in the templates provides a brush canvas for drawing the mask, and an ImageCompare node shows the before/after result side by side. The Painter node is only available under Nodes 2.0; if you only see “Painter: Node 2.0 only”, enable Nodes 2.0 via Menu -> Nodes2.0, or use the Mask Editor to create the mask instead.
To use the Partner Nodes, you need to ensure that you are logged in properly and using a permitted network environment. Please refer to the Partner Nodes Overview section of the documentation to understand the specific requirements for using the Partner Nodes.
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

​
Bria: Eraser

Remove a specific object or region from an image. The masked area is erased and filled with surrounding context; everything outside the mask stays unchanged. Bria: Eraser workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Bria Eraser” in Template Library
Input materials Upload this file to the matching LoadImage node:

vintage_girl_yellow_apple.png

Download sample input image
Bria: Eraser inputBria: Eraser example output
How to use
  1. Load an image: Upload your image in LoadImage. The Painter canvas and compare view auto-update.
  2. Paint a mask: Brush over the object or region you want to remove. Paint slightly beyond the object’s edge (hair, glass, fabric, contact points) so the model has room to blend cleanly.
  3. Run BriaEraser: No prompt needed. The node erases the masked area and inpaints the background. Enter your api_key if it is not already set.
  4. Compare and save: ImageCompare shows before/after, SaveImageAdvanced exports the result.
The masked area is fully regenerated from its surroundings, so the result blends seamlessly. The mask is binary: white (255) marks the region to erase, black (0) everywhere else, and it must match the image’s aspect ratio. For more precise results, use an automatic segmentation mask (SAM-style) if available: the API’s mask_type distinguishes manual (brush-drawn) from automatic (algorithm-generated) masks.

​
Bria: Expand Image

Expand an image beyond its original borders. The original image stays untouched; the surrounding area is generated to match its lighting, perspective, and texture. Bria: Expand Image workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Bria Expand Image” in Template Library
Input materials Upload this file to the matching LoadImage node:

red_sports_car_night.png

Download sample input image
Bria: Expand Image inputBria: Expand Image example output
How to use
  1. Load an image: Upload your image in LoadImage and connect it to BriaExpandImage.
  2. Choose an expansion mode in the expand_mode dropdown:
    • Preset aspect ratio: Pick one of 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9. The image is centered and the edges are expanded to fit that ratio.
    • Custom ratio: Pick custom_ratio and set ratio_width / ratio_height (e.g. 21 and 9 for 21:9). Bria accepts width-to-height ratios between 0.5 and 3.0, so anything taller than 1:2 needs the manual mode.
    • Manual: Pick manual and place the original image on a canvas with canvas_width / canvas_height (max 5000 x 5000), image_width / image_height, and image_x / image_y (the image’s top-left corner; can be negative to crop).
  3. Prompt (optional): Leave it empty and Bria automatically generates a prompt from the input image and expands to match its scene and style. Or write your own to guide the expansion direction explicitly, for example “the street continuing to the right”, “add a streetlamp”, “no other cars”. English only; special characters are not supported.
  4. Optional: negative_prompt to avoid unwanted content, seed to reproduce a result, moderation to enable content moderation.
  5. Save: Connect the image output to SaveImage.
The prompt output on the node shows the prompt actually used: your input, or the one auto-generated by Bria when the field is empty. If the target aspect ratio equals the image’s current ratio (e.g. a 1:1 image set to 1:1), no changes are made and the image is returned as-is. Canvas area is limited to 5,000 x 5,000 pixels. Keep the main subject above 15% of the total canvas area for best results.

​
Bria: Generative Fill

Regenerate a specific region of an image from a prompt. The masked area is fully regenerated; everything outside the mask stays pixel-perfect unchanged. Bria: Generative Fill workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Bria: Generative Fill” in Template Library
Input materials Upload this file to the matching LoadImage node:

retro_girl_cinnamon_bun.png

Download sample input image
Bria: Generative Fill inputBria: Generative Fill example output
How to use
  1. Load an image: Upload your image in LoadImage. The Painter canvas and compare view auto-update.
  2. Paint a mask: Brush over the region you want to regenerate. Blob-shaped, brush-drawn masks work best. Paint slightly beyond the object’s edge (hair, glass, fabric, contact points) so the model has room to blend.
  3. Write the prompt: In BriaGenFill, describe what should be generated inside the masked area, as if art-directing a cropped micro-scene: name the object, its material and size, how it interacts with the surface, and ask for a contact shadow. Around 90-110 words works best. Keep refine_prompt enabled.
  4. Optional: negative_prompt to avoid unwanted details. Use a fixed seed to iterate on the mask or wording, then randomize once the result looks right.
  5. Compare and save: ImageCompare shows before/after, SaveImageAdvanced exports the result.
Masks trigger generative replacement, not pixel retouching: the masked area means “regenerate this region”, not “touch up this region”.

​
Get started

  1. Update ComfyUI to the latest version
  2. Go to Template Library, search for Bria Eraser, Bria Expand Image, or Bria Generative Fill