Changelog

AVIF Support in Try-On Studio

• The Try-On Studio now supports AVIF image inputs.

Improved Reliability via Redundant Processors

• We’ve implemented additional 3rd party processor backups to significantly reduce the occurrence of ThirdPartyError messages and boost system resilience.

• Native 864 × 1296 px outputs (≈1 MP) – 50% more pixels than v1.5 for crisper fabric textures, sharper prints, and cleaner edges.

• Upgraded “Quality” mode – Stronger identity preservation with truer skin tones, better top-and-bottom continuity, and more faithful recovery of original garments.

• Runtime-optimized presets

  • Performance (~7 s): v1.5-level speed with visibly sharper detail.

  • Balanced (~10 s): extra refinement for challenging fits and textures.

  • Quality (~19 s): maximum realism with enhanced lighting, anatomy, and garment integration

How to Access FASHN v1.6

Web App: FASHN v1.6 is now the default model powering our Try-On Studio.

API: Please read our updated API documentation to learn how to access FASHN v1.6.

Learn more and see visual examples in our official announcement blog →

You can now view your usage and performance with our new analytics dashboard. You can find the new dashboard in /api/analytics.

• Added “Edit” button to images in My Gallery

• Added “Edit Model” button to models in the Saved Models gallery

• API Requests Page

  • Added search by Prediction ID

  • Added ability to copy Prediction ID

• Gallery

  • Added ability to copy Prediction ID

• Upgrade Plan

  • Added support for 3D Secure (3DS) cards

We’ve redesigned the entire FASHN web app with a fresh interface, new color scheme, and improved navigation across all features.

• Fully responsive: now optimized for mobile and tablet

• Updated UI for better usability and visual clarity

• Streamlined layout for faster access to tools

• Improved performance across devices

Introducing the new Edit page in the FASHN web app, empowering you to make creative adjustments or fixes to your images using natural language prompts.

Key Features:

• Prompt-Based Editing: Modify garment colors, add accessories, or change backgrounds by simply describing your desired changes.

• FLUX Kontext Integration: Leveraging the new FLUX Kontext model for high-quality, context-aware edits.

• Available on All Plans: This feature is accessible to all users, regardless of subscription level.

Try it out now: https://app.fashn.ai/edit

You can now use either a custom prompt or one of your saved consistent models when swapping in Model Swap Studio.

We’ve added support for Consistent Models in the FASHN web app. This feature enables users to maintain visual consistency across generated outputs by training custom models or using FASHN’s pre-trained house models.

What’s New:

• Custom Model Training (Agency Plan only): Upload 8–20 close-up images to train a personalized model in 3–5 minutes.

• In-House Consistent Models (All Plans): Use pre-trained models — Felix, Fei-Fei, and Faye — directly in the Models Studio.

• Model Management: Train and manage multiple consistent models for different styles, campaigns, or seasonal needs.

• Integration Support: Trained models will be compatible with existing and upcoming features such as Model Swap, Image Reference, and Flat-lay to On-model workflows.

Access this functionality via the Models → Create section in the web app.

We’ve released a patch to address a few issues reported by our users:

• Fixed a skin tone mismatch that could occur when switching from a long sleeve top to a short sleeve top, where the wrist area didn’t seamlessly blend with the newly generated skin.

• Resolved background discontinuities that were sometimes visible with certain background types.

Building on our May 3, 2025 update, we’ve further refined our algorithms to improve identity preservation. This update brings better retention of individual features such as skin tone, freckles, tattoos, and other distinguishing details — as well as improved handling of original, unswapped garments.

We’ve added two new parameters to give you more control over image delivery:

• output_format: Choose between 'png' (highest quality) and 'jpeg' (faster, optimized for real-time use cases like virtual fitting rooms). Default: 'png'.

• return_base64: When set to true, the API returns a base64-encoded image string instead of a CDN URL — ideal for fully private, ephemeral use. Default: 'false'.

Check out the updated API docs for usage details.

We have significantly enhanced the 'Quality' mode, focusing on preserving skin details and original garment integrity. This update delivers noticeable improvements in the following scenarios:

1. Preservation of Unique Skin Characteristics:

   • Improved retention of original model features such as tattoos, freckles, wrinkles, and other distinctive skin attributes.

2. Enhanced Garment Reconstruction:

   • Superior reconstruction when significantly altering garments. For example, changing a long top into a crop top now results in better imagining of underlying garments, ensuring realistic and consistent results.

3. Improved Bottom Garment Retention:

   • Enhanced handling of minimal bottom garments (e.g., underwear or panties) to prevent unintended conversion into shorts. Minimal garments are now preserved accurately during top garment changes.

4. Reduced Distortion in Non-swapped Regions:

   • Major improvement in maintaining original garment details when changing bottom garments. The top garments now experience significantly reduced distortion, preserving the original appearance and details

You can now select multiple images in your gallery to delete them all at once. Deleting generated videos is also supported.

1MP outputs and flexible input aspect ratios are now supported in both the API and Web App