Shot by Text - Automatic
Seven scene ideas from one description
- image
- output_image_1
- output_image_2
- output_image_3
- output_image_4
- output_image_5
- output_image_6
- output_image_7
ShotByTextAutomatic (shown as Shot by Text - Automatic) is the idea-generator of Bria's product-shot family. You give it a product photo and a written scene description; it returns up to seven different compositions - different placements, sizes, and scene interpretations - all from one API call. It's the text-driven cousin of ShotByImageAutomatic, and it's the node to start with when you're brainstorming a catalog and want to see what the model thinks looks good before you commit to a layout.
How it works
Inputs: image (product) and scene_description (what the scene should be), plus shot_size (default 1000, 1000 as width, height). The node calls Bria's /v1/product/lifestyle_shot_by_text endpoint with the automatic placement type, letting the model compose the product freely within the canvas. The text controls carry over from ShotByTextOriginal: mode (base / fast / high_control, default fast), optimize_description (default true), exclude_elements, plus force_rmbg and content_moderation.
Output is output_image_1 through output_image_7. The API returns what it generates (up to seven); leftover sockets are padded with None and just stay empty - normal behavior, not a fault.
Installing it
Part of the BRIA AI API nodes pack (Bria-AI/ComfyUI-BRIA-API). ComfyUI Manager → search BRIA API → install, or:
cd ComfyUI/custom_nodes
git clone https://github.com/Bria-AI/ComfyUI-BRIA-API
Restart ComfyUI; it's under API Nodes. No downloads, no GPU - cloud call needing a BRIA API token from platform.bria.ai. One billed generation per run regardless of how many candidates come back.
Practical notes
This is the lowest-effort node in the ShotBy family for getting a spread of ideas, but the seven outputs are a mixed bag by design - you'll want to eyeball every socket, not just output 1. high_control mode is your friend when the description is detailed and you want it honored rather than improvised; fast is fine for scouting. If you find a description that produces good scenes but the product keeps landing awkwardly, stop fighting it here - switch to Manual Placement or Custom Coordinates to pin the product down while keeping the text-driven background.
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | BRIA_API_TOKEN | — |
| image | IMAGE | — | |
| scene_description | STRING | — | |
| mode | COMBO | fast | 3 options: base, fast, high_control |
| shot_size | STRING | 1000, 1000 | — |
| force_rmbgopt | BOOLEAN | false | — |
| content_moderationopt | BOOLEAN | false | — |
| optimize_descriptionopt | BOOLEAN | true | — |
| exclude_elementsopt | STRING | — |
Outputs (7)
| Name | Type | Description |
|---|---|---|
| output_image_1 | IMAGE | — |
| output_image_2 | IMAGE | — |
| output_image_3 | IMAGE | — |
| output_image_4 | IMAGE | — |
| output_image_5 | IMAGE | — |
| output_image_6 | IMAGE | — |
| output_image_7 | IMAGE | — |