What's new at FASHN AI

New Input Parameters: image_context and mask

The Edit API endpoint has been expanded with additional capabilities. Alongside the newly introduced Image Context support, the endpoint now also accepts a mask parameter, enabling the same Brush Edit functionality available in the app.

The mask can be combined with Image Context to perform precise, localized edits guided by a reference image. This allows targeted changes such as placing logos, modifying buckles, or applying embroidery with greater accuracy.

New Runtime Error Type: UnavailableError

We’ve also improved error handling across the API and introduced a new UnavailableError. This error explicitly indicates temporary service unavailability or overload, making it easier to implement appropriate handling strategies such as retries with backoff or fallback workflows.

For more details see our API documentation: Edit API reference: https://docs.fashn.ai/api-reference/edit Error handling: https://docs.fashn.ai/api-overview/error-handling

Face Reference, our core feature for maintaining model consistency across Product to Model, Model Swap, and Model Creation, is now available to all plans.

Previously limited to Agency users, Face Reference can now be used by everyone through a curated set of pre-created realistic AI faces designed by the FASHN team. The initial release includes 4 faces (2 male, 2 female), with more planned in future updates.

This allows all users to experience model consistency workflows and understand how Face Reference works, without needing to upgrade to Agency just to try this feature.

Agency users retain full access to advanced capabilities, including creating custom AI faces and uploading their own images to apply unique identities to photoshoots.

The Edit tool and API endpoint now support Image Context, an optional reference image that provides visual guidance when text instructions alone are not sufficient.

Image Context can be used to:

• Apply a specific background from a reference image

• Mimic complex poses or viewpoints

• Transfer patterns, textures, or color characteristics

For best results, Balanced 4K and Creative 4K are recommended when using Image Context, as they handle visual reference guidance more reliably. Precise 1K remains effective for common tasks such as background or pose changes, but may be less reliable for detailed texture or material transfers.

This addition reduces the need for complex prompting and enables faster, more predictable editing workflows across both the app and API.

Create Face now offers ⚖️ Balanced 4K as an additional generation option. This allows you to create more realistic and diverse faces using the Balanced 4K pipeline.

The Try On tool has been significantly reworked to match the quality, control, and aesthetics of the upgraded Product to Model, Model Swap, and Edit tools. It now integrates more naturally into workflows where you need to place new garments on a specific model photo or maintain identity across a campaign.

Higher Fidelity and Stronger Model Consistency

Try On is now a stronger option for model consistency, allowing you to pair new products with existing models while preserving their identity. It continues to excel when transferring garments from images where they are already being worn, offering a more faithful result than Product to Model in these scenarios.

Expanded Product Support

While optimized for apparel, the tool now handles a wider range of wearable items, including scarves, shoes, headwear, eyewear, and more.

Up to 4K Resolution

Try On now supports up to 4K output, ensuring the tool no longer limits the quality of your assets.

This upgrade comes with two trade offs:

• Runtime is now approximately 30–40 seconds per request

• Credit cost has increased from 1 to 2 credits

Pro and Agency users can now choose the resolution used for image to video generation. Previously, Pro users were locked to 720p and Agency users defaulted to 1080p, even though each resolution has a different credit cost (480p = 1 credit, 720p = 3 credits, 1080p = 6 credits).

With this update, users who prefer producing more videos at a lower cost can now do so:

• Pro users can choose between 720p and 480p

• Agency users can choose between 1080p, 720p, and 480p

The resolution selector appears in the same Gallery interface used before, now with additional options for choosing the desired output quality and credit usage.

Creative 4K has been significantly improved. It now offers better prompt control and noticeably sharper visuals, reducing the grainy or dreamy look seen in earlier versions. While it remains less controllable than Precise 1K and Balanced 4K, Creative 4K continues to deliver effortless, editorial style images that many users prefer for lifestyle and campaign work.

This update also brings greater diversity in generated faces. Previous versions of Creative 4K tended to converge toward similar facial features, but the new model now produces a much wider range of identities.

The credit cost remains unchanged. Runtime may be slower for the next 1 to 2 weeks as we measure the demand for this new resolution mode.

Face Reference and Face Swap now support 2K resolution. These features were previously limited to Precise 1K, and although they do not yet operate at full 4K, they can now be used alongside the 4K resolution modes (Balanced 4K or Creative 4K) while still producing consistent identities at 2K.

How to Use It

Face Reference and Face Swap continue to work the same way as before. The key difference is that the 4K resolution options are no longer disabled in tools such as Product to Model or Model Swap. You can now select a 4K mode, and the system will return a consistent model at 2K, giving you higher fidelity identity control without compromising product accuracy.

The FASHN AI Assistant has been upgraded beyond simple tool routing. Previously, the assistant identified the correct tool and directed you to it. It can now run supported tools on your behalf, letting you generate results directly within the chat.

This capability is currently in Beta, and more tools will be added over time. Our goal is to enable a full workflow entirely through the assistant for those who prefer a chat based interface.

This upgrade also prepares the assistant for efficient use in our upcoming mobile app.

The Edit tool from the app is now available as an API endpoint. Edit is a versatile post processing method that preserves identity and product fidelity while executing freeform instructions. It can be used to adjust poses or viewpoints for additional angles, apply styling such as accessories or lighting, or correct issues from outputs generated with Product to Model or Model Swap.

Edit can also produce results similar to Product to Model in scenarios that are not centered on fashion or human models. This makes it suitable for a wide range of use cases, including home products, furniture, pet accessories, and other non apparel items.

API reference: https://docs.fashn.ai/api-reference/edit