Shot by Text - Automatic Aspect Ratio
Describe a scene into a target format
- image
- output_image
ShotByTextAutomaticAspectRatio (shown as Shot by Text - Automatic Aspect Ratio) is the text-driven shot node that generates directly into a target aspect ratio. Give it a product photo and a scene_description, pick the ratio, and Bria builds the scene in that shape - one finished output, no cropping after the fact.
It's the sibling of ShotByTextAutomatic (which returns seven free-composition candidates at a fixed pixel size). This one returns a single image at a chosen ratio, which makes it the right tool when the deliverable format is already decided: 9:16 for Reels/TikTok, 16:9 for a banner, 1:1 for a listing grid. You're trading the variety of the seven-candidate node for a layout that's guaranteed to fit.
How it works
Inputs: image (product), scene_description, and aspect_ratio - nine options (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9), default 1:1. It calls Bria's /v1/product/lifestyle_shot_by_text endpoint with the automatic_aspect_ratio placement type. Text controls carry over: mode (base / fast / high_control, default fast), optimize_description (default true), exclude_elements, plus force_rmbg and content_moderation. One output: output_image.
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, billed per generation.
Practical notes
Because you get exactly one result, your scene description does double duty - it has to both describe the environment and leave room for the product to sit naturally at that ratio. For very tall or very wide ratios, describe the space accordingly ("wide open counter with empty space on the right" for a 16:9). Use high_control mode when the layout matters and the first fast pass keeps disappointing. If the product keeps landing awkwardly despite the right description, move to Manual Placement and control the position yourself.
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 |
| aspect_ratio | COMBO | 1:1 | 9 options: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, +3 |
| force_rmbgopt | BOOLEAN | false | — |
| content_moderationopt | BOOLEAN | false | — |
| optimize_descriptionopt | BOOLEAN | true | — |
| exclude_elementsopt | STRING | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| output_image | IMAGE | — |