- Platform
- Web App
- Duration
- 12 weeks
- Industry
- Healthcare / Aesthetics / AI
- Read time
- 5 min read
The undecided consultation is the most expensive moment in any transformation service business. A client sits across from a practitioner, genuinely interested, but unwilling to commit because they cannot picture the result on their own face, their own hair, or their own space.
Stock before-and-after photos help, but they feature someone else. Makeover generates the preview using the client's own photo. The result lands differently: it is personal, it is theirs, and it closes the gap between "I'm interested" and "let's book."
Dental practices, aesthetic clinics, hair salons, and interior designers in 40+ transformation categories use Makeover to show what the outcome looks like before the client says yes. Consultation-to-booking conversion increased 35% for practices using it.
before & after
What changed
- Service businesses showed stock before-and-after photos of models, and clients could not see themselves in the outcome, so hesitation remained
- Consultation-to-booking conversion of 40 to 55% left significant qualified interest leaving without committing
- Creating a personalized preview required a skilled photo editor and 30 to 45 minutes per client. Too expensive to do at scale, so most practices skipped it entirely
- Clients who left a consultation undecided had no personalised follow-up to bring them back
- Practitioners had no way to show multiple treatment options in the same consultation without extensive manual work
- Clients see a photorealistic preview using their own photo in under 60 seconds during the consultation
- Practitioners show two or three variations (lighter vs. heavier treatment, one approach vs. another) in the same session so clients choose rather than guess
- Previews are saved to the client record and linked to their profile for comparison at future visits
- Clients who leave without booking receive a follow-up message with their personalised preview attached
- 40+ service categories supported with category-specific AI models trained on real transformation pairs
What we had to solve
- 01
Getting previews realistic enough that clients trust them without overselling
An AI preview that looks obviously artificial does more damage than no preview at all: it signals that the practice is using technology it does not fully control. The output had to look realistic at consultation viewing distance on a tablet, which meant training category-specific models on real before-and-after pairs rather than using a general image generation approach. Dental whitening, hair color, aesthetic contouring, and interior finishes each required a model that understood the texture, depth, and lighting characteristics of that specific transformation. Getting the quality bar right for each category was the core research challenge.
- 02
Generating the preview fast enough for use during an active consultation
A preview that takes five minutes to generate is not a consultation tool. It is a disruption. The entire flow had to complete in under 60 seconds: photo capture, upload, inference, and display back to the practitioner and client. That required a job queue architecture that could route requests to the right category model, handle inference retries without adding visible latency, and deliver the result directly to the consultation interface without requiring a page refresh. Replicate's GPU infrastructure handled the inference; the engineering challenge was the end-to-end latency budget.
outcomes
What we achieved
Undecided clients were leaving without booking. Generic stock photos could not personalise the outcome for a specific client.
Manual editing took 30 to 45 minutes per client preview. Most practices skipped it entirely because the cost per consultation was too high.
Dental, aesthetics, hair, interiors, landscaping: each category needed a model trained on its specific transformation type.
Your consultations are losing undecided clients who cannot picture the result?
the build
What we built
Makeover is built around a core insight: the preview has to look like the client, not like a model. Anything that reads as templated or artificial undermines trust at the moment it matters most.
Client sees a photorealistic result in under 60 seconds — trained on real before-and-after pairs
The client uploads a photo or it is captured on a tablet in the consultation room. Makeover runs the image through a category-specific AI model (dental, hair, aesthetics, interiors) and returns a photorealistic result in under 60 seconds. The model is trained on real before-and-after pairs for each category, not on general image generation data.
Clients express a preference rather than committing blindly to one fixed outcome
Practitioners show multiple versions in the same session: lighter vs. heavier treatment, one approach vs. another. The client sees options rather than a single fixed outcome, which supports a more natural consultation conversation and allows the client to express a preference rather than committing blindly.
Returning clients compare new previews against previous sessions — no file hunting before appointments
Previews are saved to the client's record and linked to their profile. Returning clients can compare a new preview against previous sessions. Practitioners access the image history before a follow-up appointment without hunting for a saved file.
Clients who leave without booking get a reminder with their own preview — not a generic brochure
After the consultation, the practitioner sends the client their personalised preview via email or SMS. Clients who leave without booking receive a reminder with their preview attached, a follow-up that is personal because the image is theirs, not a generic brochure.
Want results like these for your business?
stack
Why we chose this stack
- 01Next.jsThe practitioner dashboard and client-facing share pages needed fast initial loads with optimistic UI updates so the consultation flow did not stall while waiting for the inference result to arrive.
- 02ReplicateCategory-specific image generation models run on Replicate's GPU infrastructure. Replicate's API allowed us to deploy separate fine-tuned models for each transformation category without managing GPU servers.
- 03AWSPreview images are stored on S3 with signed URLs that expire after 30 days, keeping client photos secure and ensuring share links sent to clients cannot be accessed indefinitely.
- 04Node.jsThe job queue manages inference requests, routes each job to the correct category model, handles retries for failed inference calls, and delivers the completed preview back to the practitioner dashboard without requiring a page reload.
Common questions about Makeover
At normal consultation viewing distance on a tablet or screen, the previews read as realistic. The AI is trained on real before-and-after pairs for each category, which helps it learn the texture and depth characteristics specific to each transformation type. Practitioners are encouraged to describe previews as "an indication of the expected result" rather than a guarantee. The preview is a conversion tool, not a clinical commitment.
The core categories with dedicated models are: dental (whitening, alignment, veneers), aesthetics (Botox, fillers, contouring), hair (colour, cut, extensions), and interior design (paint, furniture layout). Additional categories are supported with a general transformation model. New category models are added based on demand from active users.
Client photos and previews are stored in the practice's account. The practice owns all client data. Photos are processed for preview generation and retained only as long as the client record exists. They are never used to train any shared model or accessed for any purpose other than generating the client's own preview.
Yes. Makeover has a widget embed and an API. The widget drops into an existing patient portal or booking page. The API lets you trigger preview generation from within your CRM or practice management software and retrieve the result URL to display inline without leaving the existing workflow.
We built the core Makeover platform (inference pipeline, multi-category model routing, practitioner dashboard, client record storage, and share flow) in 12 weeks. Adding a new service category with a dedicated fine-tuned model typically takes 3 to 5 weeks depending on the volume and quality of training data available for that transformation type. Categories with limited real before-and-after pairs take longer to achieve consistent output quality. Contact us to discuss your specific category requirements.
Related work