AutoNoma
Back to Portfolio
Content and Video33 nodes

AI Photo Clone Automation

Train a personal photo model and generate on brand images

Trains a Flux LoRA from your photos once, then generates new images in your style on demand. Includes captioning and publishing steps.

Replicate Flux LoRA TrainerTelegramOpenAICode
One time trainingOn demand generationCaption to publish

Preview image

Workflow preview will appear here

Download workflow
What It Does

A system that works while you are not looking

This workflow creates a personal image model from your own photos, then uses it to generate new images that look like you in different settings. You upload a set of portraits once to train a Flux LoRA. After that, you can ask in Telegram for a new image with a prompt like founder portrait in a modern office, and it will generate it in your style, write a caption and queue it for publishing. It is ideal for founders who want consistent, recognizable visuals without repeated photo shoots.

A reusable personal model that turns text prompts into on brand portraits and posts.

Outcome
How It Works

A manual trigger starts training. Photos are sent to Replicate to create a model and start a LoRA training job with the Flux dev trainer. The workflow polls the training status until complete. A Telegram trigger handles generation. Your prompt is combined with the trained model reference and sent to Replicate for prediction, polled until the image is ready. A second branch uses OpenAI to write a social caption. Both image and caption are logged and can be sent to Telegram for approval or pushed to a publishing step.

JourneyScroll to draw

Trigger

Inbound signal starts the flow

Orchestrate

Models, tools and branches run

Deliver

Result logged and returned

Who it is for

Creators, media teams and brands that repurpose one asset into many at scale.

What you save

Hours become minutes per task, handoffs stay consistent in Sheets or CRM, and the workflow file is yours to own. Import, add your keys and run.