I will build a custom comfyui workflow or ai image pipeline for your brand


Level 2
Vetted by Fiverr Pro
Thierry B was selected by the Fiverr Pro team for their expertise.
About this gig
You don't need another prompt. You need a pipeline that gives the same result on Monday and on Friday, with your product intact.
I build ComfyUI workflows for teams that produce images at volume: e-commerce catalogs, fashion on-model shots, product scenes, consistent characters. Each one is tested on your files and handed over with docs.
WHAT YOU GET
Custom workflow (JSON) built around your use case and your hardware or cloud
Product and identity lock: your reference stays pixel-faithful, only the scene changes
Batch processing, naming conventions, output folders ready for your shop
Docs and a video walkthrough your team can follow
Standard and Premium: brand presets, custom LoRA training, cloud or API deployment on your own account (you keep the keys)
WHO IS DOING IT
20 years as a creative director in Paris agencies, now running AI production full time. These workflows produce my own Fiverr client work every week. Fiverr Pro vetted.
HOW IT WORKS
Step 1: You describe the output you need and send 5 to 10 sample inputs
Step 2: I send a pipeline map in 48 hours, you validate
Step 3: Build, test on your files, hand over with docs
Message me with your use case before ordering.
Delivery style preference
Please inform the freelancer of any preferences or concerns regarding the use of AI tools in the completion and/or delivery of your order.
Get to know Thierry B
20 years as a Paris creative director making AI visuals true to your product
Level 2
Thierry B is part of the Fiverr Pro catalog and has been hand-picked by a dedicated Fiverr Pro team for their skills and expertise.
Vetted for
AI Art
Video Art Creation
- FromFrance
- Member sinceJan 2025
- Avg. response time1 hour
- Last delivery1 month
Languages
English, French, Spanish, Japanese
My Portfolio
Other AI Art Services I Offer
FAQ
Do I need a GPU?
No. I can set it up on your cloud account (serverless or dedicated) or on your machine. You keep ownership of the accounts and the keys.
Which models?
Open models by default so nothing depends on a subscription: SD, Flux, Wan and their LoRAs. Commercial APIs can be plugged in if you prefer.
Can you train a LoRA for my product or character?
Yes, included in Premium or as an extra. 15 to 30 good photos are enough.
Do you teach my team?
Yes. Every package includes a recorded walkthrough. Premium includes a live training session.

