Face Reference

Face Reference is a dedicated feature that maintains identity across Product to Model, Model Swap, Create Model, and Face Swap. It keeps generations aligned with a single face image and works more reliably and easily than methods like fine-tuning or training on a set of images.

Why Face Reference instead of fine-tuning

Earlier versions of FASHN supported consistency through fine-tuning (custom training) on about 8 to 12 images of an individual. Although training can work, it is difficult to do well. Each source image can introduce bias, and the underlying model becomes less flexible after fine-tuning. Customers also found it challenging to gather a complete and consistent training set in the first place, since they needed consistent results before they could produce the required images.

After several months of testing with customers, we found that anchoring identity to a single face reference produces more reliable results, avoids dataset collection issues, and maintains the flexibility of the base model.

How Face Reference works

Face Reference influences supported tools in two ways:

• It guides the base generation to match visible appearance traits from the reference, including skin tone and complexion, facial features, hair, and apparent age range.
• It reinforces the likeness with special focus on facial features.

Face Reference adapts identity to new angles, expressions, hairstyles, and lighting. It keeps the identity consistent while still allowing the model to generate natural, flexible, and creative variations.

Where to use it

• Product to Model: Generates a model that reflects the face reference across the full body. Visible traits such as skin tone, complexion, and apparent age range remain consistent across the face and body.
• Model Swap: Replaces the existing model with the face reference and updates exposed skin and other visible appearance traits across the body to remain consistent with it.
• Create Model: Builds a new model from scratch that resembles the face reference, with full-body alignment from the start.
• Face Swap: Includes a Face Swap variant focused on restoring identity rather than altering it. Use it when pose, background, or other edits distort the face. It can also swap identities, but the underlying model must already match the new face in skin tone and age.

Additional controls

Face Reference adds a control that adjusts how strongly the result follows the reference image versus the base image or prompt:

• All supported tools show Match Reference.
• You will also see Match Base or Match Prompt, depending on whether the input starts from an image or a prompt.

Example (Model Swap): If the current model faces left and smiles, but the face reference looks straight ahead with a neutral expression, the control lets you decide whether to keep the existing pose and expression or follow the reference more closely.

Example (Product to Model): The control decides how much the prompt affects the result. For instance, a prompt such as "a model looking up" can shift pose and expression unless you set the control to follow the reference image more strongly.

Preparing reference photos

• Even though the feature can adapt to new angles or expressions, results improve when the reference photo already resembles the expected output. In these cases, keep the Match Reference control at its default setting to maximize resemblance.
• Hair, makeup, and accessories should be close to the desired final look.
• Avoid heavy occlusions such as sunglasses, masks, or hands covering the face.

Choose a reference source

• Portrait Elements: Choose a curated portrait directly from the Face Reference field.
• Custom reference images: Upload a face image or select one from Gallery.

If needed, upscale a custom reference before using it to improve facial detail.

Effect on runtime and cost

Face Reference is computationally heavy and increases both generation time and credit cost. Enabling Face Reference adds +2 credits per output image. See App Pricing for the full cost breakdown.

Limitations

Face Reference works best at 2K resolution or below, where identity and product details are retained most reliably. You can still select 4K, but fine facial and product features may be harder to preserve at higher resolutions.

Workflow summary