add examples + fix lifestyle shot by text reference to handle urls#32
Open
Gilad-brudner-bria wants to merge 13 commits intoBria-AI:devfrom
Open
add examples + fix lifestyle shot by text reference to handle urls#32Gilad-brudner-bria wants to merge 13 commits intoBria-AI:devfrom
Gilad-brudner-bria wants to merge 13 commits intoBria-AI:devfrom
Conversation
Prompts cover: capability tour, product shot pipeline, sketch to business asset, precision edit chain, post-production pipeline, and building a product pipeline in code. Each visual prompt includes an HTML gallery output for step-by-step results. https://claude.ai/code/session_01Jmbhgbcp2QW1rnbjR8DUyd
Product shot & post-production prompts now use Bria sandbox asset. Sketch prompt now uses ibb.co hosted sketch image. https://claude.ai/code/session_01Jmbhgbcp2QW1rnbjR8DUyd
The cabin scene caused background removal to only extract the sky. Changed to a red sneaker on white background, which gives RMBG a clean subject to extract and makes the full pipeline work end-to-end. https://claude.ai/code/session_01Jmbhgbcp2QW1rnbjR8DUyd
…restyle - Changed from white background to gym wooden floor so background removal actually demonstrates its value - Changed oil painting restyle to retro comic book illustration, which is more relevant for a sneaker https://claude.ai/code/session_01Jmbhgbcp2QW1rnbjR8DUyd
Higher resolution starting image produces better results through the downstream pipeline steps. https://claude.ai/code/session_01Jmbhgbcp2QW1rnbjR8DUyd
The endpoint accepts image_url (URL) in addition to file (base64). When a URL is available, image_url should be preferred. Updated SKILL.md quick reference and api-endpoints.md with correct parameter names (image_url, scene_description) and a full parameters table. https://claude.ai/code/session_01Jmbhgbcp2QW1rnbjR8DUyd
Keep only the essential parameters: image_url, file, scene_description. https://claude.ai/code/session_01Jmbhgbcp2QW1rnbjR8DUyd
…apabilities-DYB1H Claude/document skill capabilities dyb1 h
galbria
reviewed
Mar 23, 2026
Contributor
galbria
left a comment
galbria
left a comment
There was a problem hiding this comment.
good but we also need to test it
| { | ||
| "file": "BASE64_ENCODED_IMAGE", | ||
| "prompt": "modern kitchen countertop, natural lighting", | ||
| "image_url": "https://product-with-transparent-bg.png", |
Contributor
There was a problem hiding this comment.
should be file cuz most ppl edit local files.
if its a url the agent will fetch the image but if it local it will not be able to upload it
Comment on lines
+44
to
+67
| ## Getting Started — Try These Prompts | ||
|
|
||
| Copy-paste any of these to see Bria in action: | ||
|
|
||
| ### See What Bria Can Do | ||
| > Generate a 4MP photo of a red sneaker on a wooden floor in a gym. Then show me what you can do with it — one step at a time: remove the background, replace the background with a city street scene, restyle as a retro comic book illustration, change the season to winter, and relight with golden hour. Save each result and create a simple HTML page showing every step with a label. | ||
|
|
||
| ### Product Shot Pipeline | ||
| > I have a product image at `https://labs-assets.bria.ai/sandbox-example-inputs/pexels-the-glorious-studio-3584518-5370644.jpg`. Remove the background, place it in a modern kitchen as a lifestyle shot, and upscale to 4x resolution. Then expand it to 1:1 for Instagram, 9:16 for Stories, and 16:9 for a website hero banner. Save each step and create a simple HTML page showing the progression. | ||
|
|
||
| ### Sketch to Business Asset | ||
| > I have a rough sketch of a brand mascot at `https://bria-datasets.s3.us-east-1.amazonaws.com/gb_assets/generated-image.png`. Convert it to a polished colored illustration, enhance the quality, then create versions restyled as a 3D render and as vector art. Save each version and create a simple HTML page showing each result with a label. | ||
|
|
||
| ### Precision Edit Chain | ||
| > Generate a photo of a modern office reception area. Then make these edits one by one, showing me the result after each: add a small bonsai tree on the reception desk, replace the wall art with a minimalist logo, change the lighting to warm evening, and remove the chair in the corner. Save each step and create a simple HTML page showing the image after each edit. | ||
|
|
||
| ### Post-Production Pipeline | ||
| > Take this image `https://labs-assets.bria.ai/sandbox-example-inputs/pexels-the-glorious-studio-3584518-5370644.jpg` and run a full post-production pipeline: first enhance the quality, then expand to 16:9, then upscale to total 8mp resolution. Save each step and create a simple HTML page showing before and after for each stage. | ||
|
|
||
| ### Build a Product Pipeline in Code | ||
| > Write a Python script that takes a list of product image URLs and processes each one through a pipeline: remove the background, place it in a lifestyle scene based on a prompt I provide, and upscale to 4x. For each step, poll the status URL until complete before moving to the next. Save all outputs to a local folder organized by product. | ||
|
|
||
| --- | ||
|
|
Contributor
There was a problem hiding this comment.
im not sure if they should be here and not in a different file
Comment on lines
+60
to
+76
| ### See What Bria Can Do | ||
| > Generate a 4MP photo of a red sneaker on a wooden floor in a gym. Then show me what you can do with it — one step at a time: remove the background, replace the background with a city street scene, restyle as a retro comic book illustration, change the season to winter, and relight with golden hour. Save each result and create a simple HTML page showing every step with a label. | ||
|
|
||
| **Batch assets?** Ask: "Generate product photos for these 5 items and create transparent PNGs for each" | ||
| ### Product Shot Pipeline | ||
| > I have a product image at `https://labs-assets.bria.ai/sandbox-example-inputs/pexels-the-glorious-studio-3584518-5370644.jpg`. Remove the background, place it in a modern kitchen as a lifestyle shot, and upscale to 4x resolution. Then expand it to 1:1 for Instagram, 9:16 for Stories, and 16:9 for a website hero banner. Save each step and create a simple HTML page showing the progression. | ||
|
|
||
| **Presentations?** Ask: "Create a slide visual showing data analytics, blue gradient, corporate style" | ||
| ### Sketch to Business Asset | ||
| > I have a rough sketch of a brand mascot at `https://bria-datasets.s3.us-east-1.amazonaws.com/gb_assets/generated-image.png`. Convert it to a polished colored illustration, enhance the quality, then create versions restyled as a 3D render and as vector art. Save each version and create a simple HTML page showing each result with a label. | ||
|
|
||
| ### Precision Edit Chain | ||
| > Generate a photo of a modern office reception area. Then make these edits one by one, showing me the result after each: add a small bonsai tree on the reception desk, replace the wall art with a minimalist logo, change the lighting to warm evening, and remove the chair in the corner. Save each step and create a simple HTML page showing the image after each edit. | ||
|
|
||
| ### Post-Production Pipeline | ||
| > Take this image `https://labs-assets.bria.ai/sandbox-example-inputs/pexels-the-glorious-studio-3584518-5370644.jpg` and run a full post-production pipeline: first enhance the quality, then expand to 16:9, then upscale to total 8mp resolution. Save each step and create a simple HTML page showing before and after for each stage. | ||
|
|
||
| ### Build a Product Pipeline in Code | ||
| > Write a Python script that takes a list of product image URLs and processes each one through a pipeline: remove the background, place it in a lifestyle scene based on a prompt I provide, and upscale to 4x. For each step, poll the status URL until complete before moving to the next. Save all outputs to a local folder organized by product. |
Contributor
There was a problem hiding this comment.
lets add the results of these prompts to an examples.md files
Comment on lines
+276
to
+277
| "image_url": "https://product-with-transparent-bg.png", | ||
| "scene_description": "modern kitchen countertop, natural lighting", |
Contributor
There was a problem hiding this comment.
should be file cuz most ppl edit local files.
if its a url the agent will fetch the image but if it local it will not be able to upload it
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.