# Bria Products Overview

### Image Generation

Generate high-quality, commercially-safe visuals using Bria's state-of-the-art models.

**Next-Generation Image Generation (FIBO Architecture):**

Our latest API offers precise control via **structured JSON prompts**, utilizing a two-step process: a **VLM Bridge** translates your input into a detailed instruction, which the **FIBO image model** uses for generation.

**Choose Your Pipeline:**

* **Standard Pipeline (Recommended):**
  * **Best for:** Maximum nuance, instruction adherence, and visual fidelity.
  * **Uses:** Gemini 2.5 Flash Bridge + Full FIBO Model.
  * **Endpoints:** `/image/generate`, `/structured_prompt/generate`
* **Fibo Lite Pipeline:**
  * **Best for:** Speed, efficiency, and data sovereignty.
  * **Uses:** FIBO-VLM Bridge (Open Source) + Fibo Lite Model.
  * **Benefits:** Both components are optimized for **rapid inference**. This combination enables **fully local, on-prem deployment** for privacy-critical environments.
  * **Endpoints:** `/image/generate/lite`, `/structured_prompt/generate/lite`


**Capabilities:**

* Generate new images from text or reference images.
* Refine or recreate previous generations using their `structured_prompt`.
* Optionally generate *only* the `structured_prompt` for inspection, editing, automation, or hybrid workflows.


**[Dive into the Docs](https://docs.bria.ai/image-generation)**

### Tailored Generation:

The Tailored Generation APIs allows you to manage and train Tailored Models that preserve and faithfully reproduce your visual IP (photos, illustrations, vectors). You can train Tailored Models through our Console or implement training on your platform via API. Check out our Console [here](https://platform.bria.ai/console/tailored-generation).

#### Training Process Overview

To train a tailored generation model:

1. **Create a Project**: Use the `/projects` endpoint to create a project and define your IP type and medium.
2. **Create a Dataset**: Use the `/datasets` endpoint to create a dataset within your project.
3. **Generate an Advanced Caption Prefix**
4. **Upload Images**: UUpload images using the `/datasets/{dataset_id}/images` or `/datasets/{dataset_id}/images/bulk` endpoints (minimum resolution: 1024x1024px).
5. **Prepare Dataset**: Review auto-generated captions and use the `/datasets/{id}` endpoint to set status to 'completed'.
6. **Create Model**: Use the `/models` endpoint to create a model, selecting either the "light" or "max" training version (Fully Automated mode) or the training parameters (Expert mode)
7. **Start Training**: Initiate training using the `/models/{id}/start_training` endpoint. Training takes 4-7 hours.
8. **Monitor Progress**: Check training status using the `/models/{id}` endpoint until status shows 'Completed'.
9. **Generate Images**: Once trained, your model can be used in multiple ways:
  - Use the `v2/image/generate/tailored` endpoint for text-to-image generation
  - Access through the Bria platform interface


**[Dive into the Docs](https://docs.bria.ai/tailored-generation)**

### Ads Generation

Bria's Ads Generation set of APIs streamlines the process of creating, managing, and customizing advertising campaigns, providing powerful tools for scalable and efficient ads and campaign generation.

These tools include:

- `/create`: Generate ads using Template IDs and content inputs, enabling rapid creation of professional-grade ad variations.
- `/brands`: Retrieve a list of brands along with their associated logos, colors, and fonts, providing the building blocks for brand-aligned campaigns.
- `/templates`: Access a list of templates, including their IDs, names, number of scenes, and a preview of the first scene.
- `/templates/{template_id}`: Fetch detailed JSON data for a specific template, including all its elements, enabling precise customization and adaptation.


**[Dive into the Docs](https://docs.bria.ai/campaign-generation)**

### Product Shot Editing

Bria offers a variety of solutions for products and apps in the eCommerce industry, which allow to enhance product imagery for online stores and product catalogs.

These solutions include:

- `/cutout`: Create clean and professional product cutouts.
- `/packshot`: Generate professional-standard packshots with customizable background colors and optimal product placement.
- `/shadow`: Add consistent and customizable shadow effects, supporting regular and floating shadows for product images with transparent backgrounds.
- `/lifestyle_shot_by_text`: Enrich product images by placing them in various environments using textual descriptions, enhancing appeal and providing context.
- `/lifestyle_shot_by_image`: Generate product images in enriched environments using a reference image for inspiration, allowing for creative and unique presentations.
- `v2/image/edit/product/integrate`: Integrate and embed one or more products into a predefined scene at precise user-defined coordinates.
- **Automotive Product Shot Editing**: Dedicated support for automotive workflows, including vehicle-specific features such as realistic reflection generation, tire and wheel refinement, environmental effects (e.g., fog, dust, snow), and harmonization presets.


**[Dive into the Docs](https://docs.bria.ai/product-shot-editing)**

### Image Editing

Bria provides a comprehensive suite of image editing routes, ranging from open-ended natural language edits (powered by our FIBO models) to specialized, task-specific AI tools.

#### Global & Structured Editing

* `/image/edit` - The master endpoint. Modify existing images using natural language or structured JSON instructions, with full support for masked local editing.
* `/structured_instruction/generate` - Translate a text instruction into a detailed JSON blueprint without generating an image (ideal for programmatic control and human-in-the-loop review).


#### Targeted Text-Driven Edits

* `/add_object_by_text` - Insert new objects into an image using natural language.
* `/replace_object_by_text` - Swap an existing object with a new one.
* `/erase_by_text` - Remove specific objects or elements by name.
* `/rewrite_text` - Change existing text within an image to a new string.
* `/blend` - Merge objects, apply textures, or rearrange items physically.


#### Style, Lighting & Atmosphere

* `/restyle` - Transform the artistic style using enum presets or custom descriptions.
* `/relight` - Modify the lighting setup (direction and atmosphere).
* `/reseason` - Change the season or weather atmosphere.
* `/colorize` - Add vivid colors to B&W photos or apply stylized color palettes.
* `/sketch_to_colored_image` - Convert a line drawing or sketch into a photorealistic colored render.


#### Background & Layout Transformations

* `/remove_background` - Remove the background to create a clean cutout with alpha preservation.
* `/replace_background` - Generate new environments using text prompts, solid colors, or reference images.
* `/blur_background` - Create a depth-of-field blur effect on the background.
* `/erase_foreground` - Erase the primary subject and generate the missing background to create an empty plate.
* `/crop_foreground` - Remove the background and crop tightly around the subject (with optional padding).
* `/expand` - Expand the image beyond its original borders (outpainting) to new aspect ratios or exact canvas sizes.


#### Mask-Based Precision Edits

* `/erase` - Erase elements seamlessly using manually created or auto-generated masks.
* `/gen_fill` - Generate new elements in a specific masked region using a textual prompt.
* `/objects/mask_generator` - Generate all possible object masks for an image, creating a full segmentation map.


#### Enhancement & Restoration

* `/enhance` - Regenerate an image with sharper textures and richer details while upscaling resolution.
* `/increase_resolution` - Authentically upscale any image without altering or hallucinating new details.
* `/restore` - Renew old or damaged photos by removing noise, scratches, and blur.


#### Presenter Modification & Specialized Tools (v1)

* `/{visual_id}/person/info` - Retrieve detailed information and available modifications for people in an image.
* `/{visual_id}/create` - Modify specific presenter attributes (e.g., age, expression, diversity, gender).
* `/{visual_id}/image_to_psd` - Create a layered PSD file from an image *(Note: Requires image registration)*.### Image Editing


Bria provides a comprehensive suite of image editing routes, ranging from open-ended natural language edits (powered by our FIBO models) to specialized, task-specific AI tools.

#### Global & Structured Editing

* `/image/edit` - The master endpoint. Modify existing images using natural language or structured JSON instructions, with full support for masked local editing.
* `/structured_instruction/generate` - Translate a text instruction into a detailed JSON blueprint without generating an image (ideal for programmatic control and human-in-the-loop review).


#### Targeted Text-Driven Edits

* `/add_object_by_text` - Insert new objects into an image using natural language.
* `/replace_object_by_text` - Swap an existing object with a new one.
* `/erase_by_text` - Remove specific objects or elements by name.
* `/rewrite_text` - Change existing text within an image to a new string.
* `/blend` - Merge objects, apply textures, or rearrange items physically.


#### Style, Lighting & Atmosphere

* `/restyle` - Transform the artistic style using enum presets or custom descriptions.
* `/relight` - Modify the lighting setup (direction and atmosphere).
* `/reseason` - Change the season or weather atmosphere.
* `/colorize` - Add vivid colors to B&W photos or apply stylized color palettes.
* `/sketch_to_colored_image` - Convert a line drawing or sketch into a photorealistic colored render.


#### Background & Layout Transformations

* `/remove_background` - Remove the background to create a clean cutout with alpha preservation.
* `/replace_background` - Generate new environments using text prompts, solid colors, or reference images.
* `/blur_background` - Create a depth-of-field blur effect on the background.
* `/erase_foreground` - Erase the primary subject and generate the missing background to create an empty plate.
* `/crop_foreground` - Remove the background and crop tightly around the subject (with optional padding).
* `/expand` - Expand the image beyond its original borders (outpainting) to new aspect ratios or exact canvas sizes.


#### Mask-Based Precision Edits

* `/erase` - Erase elements seamlessly using manually created or auto-generated masks.
* `/gen_fill` - Generate new elements in a specific masked region using a textual prompt.
* `/objects/mask_generator` - Generate all possible object masks for an image, creating a full segmentation map.


#### Enhancement & Restoration

* `/enhance` - Regenerate an image with sharper textures and richer details while upscaling resolution.
* `/increase_resolution` - Authentically upscale any image without altering or hallucinating new details.
* `/restore` - Renew old or damaged photos by removing noise, scratches, and blur.


#### Presenter Modification & Specialized Tools (v1)

* `/{visual_id}/person/info` - Retrieve detailed information and available modifications for people in an image.
* `/{visual_id}/create` - Modify specific presenter attributes (e.g., age, expression, diversity, gender).
* `/{visual_id}/image_to_psd` - Create a layered PSD file from an image *(Note: Requires image registration - [/Register](https://docs.bria.ai/image-onboarding/endpoints/register-image))*.


**[Dive into the Docs](https://docs.bria.ai/image-editing)**