Nodes/BRIA AI API nodes/Shot by Text - Manual Padding
ComfyUI Node

Shot by Text - Manual Padding

Describe a scene with air around the product

By Bria-AI·Created 2 years ago·Updated 3 months ago· 95
Shot by Text - Manual Padding
  • image
  • output_image
api_keyBRIA_API_TOKEN
scene_description
modefast
padding_values0,0,0,0
force_rmbgfalse
content_moderationfalse
optimize_descriptiontrue
exclude_elements

ShotByTextManualPadding (shown as Shot by Text - Manual Padding) is the text-driven shot node that controls layout through margins. You describe the scene in words, set padding_values for the empty space around the product, and Bria generates the shot with your product sitting in that frame of air.

Where Custom Coordinates pins the product to an exact pixel spot, this one works in margins - you decide how much breathing room surrounds the product, and the model handles the rest. It's the right tool when the product should sit centered with even space around it, and the precise canvas size is a byproduct you don't care about.

How it works

Inputs: image (product), scene_description, and padding_values - four comma-separated integers, default 0,0,0,0 (top, right, bottom, left). The node calls Bria's /v1/product/lifestyle_shot_by_text endpoint with the manual_padding 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

Same quirks as the image-driven padding node, plus a text-specific one. The default 0,0,0,0 fills the frame with product edge-to-edge, so set real values from the start; the order is top, right, bottom, left; and padding stacks on top of whatever empty space the source photo already has, so a wide product shot plus big padding equals a small product in a big scene. The text twist: your description still fills the padded area, so "minimalist scene, clean empty space" pairs with padding far better than "cluttered workshop" does. And as with all the layout variants, if margins can't get the exact framing you need, Custom Coordinates (size + position) is the precision upgrade.

CategoryAPI Nodes

Inputs (9)

NameTypeDefaultDescription
api_keySTRINGBRIA_API_TOKEN
imageIMAGE
scene_descriptionSTRING
modeCOMBOfast3 options: base, fast, high_control
padding_valuesSTRING0,0,0,0
force_rmbgoptBOOLEANfalse
content_moderationoptBOOLEANfalse
optimize_descriptionoptBOOLEANtrue
exclude_elementsoptSTRING

Outputs (1)

NameTypeDescription
output_imageIMAGE