I will do lora training and deploy comfyui workflow into serverless api, runpod

D
drong_wint
D
drong_wint
drong

About this gig

Custom AI Influencer LoRA Training

Ill train a custom LoRA for your AI influencer, with a focus on realism, consistent identity, and long-term reuse. Ideal for creators, brands, and agencies looking to build a reliable AI identity for social media, marketing, or scalable contentwithout unwanted face drift or overfitting.

Your LoRA is trained on your image dataset using a controlled process that prioritizes data quality, accurate tagging, and carefully tuned parameters. The result is designed to preserve the characters identity while allowing flexibility in style, poses, lighting, and outfits.

Youll also receive a ready-to-run ComfyUI workflow, so you can start generating without rebuilding nodes or guessing settings.

Software

ComfyUI, SDXL, FLUX, Kohya tools, and a Python-based training pipeline.

Deliverables

  • Custom LoRA model (.safetensors)
  • ComfyUI workflow (.json)
  • Prompt notes (.txt)
  • Test images (.png or .jpg)

I focus on clean, carefully tuned training and practical workflowsnot one-size-fits-all presets.

Please message me before ordering so we can review your dataset and choose the right package.





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 drong

drong

game

  • FromUnited Kingdom
  • Member sinceFeb 2026
  • Avg. response time1 hour
  • Languages

    English, Spanish, French
Hi, I’m drong — a professional FiveM/RedM developer specializing in QBCore, ESX, and VORP server setup, optimization, and troubleshooting. I build and customize full servers, premium scripts, MLO interiors, GTA V map mods, clothing/EUP, chains, tattoos, peds, and HUDs. I also fix bugs, improve performance, reduce lag, and deliver clean, stable, server-ready files with reliable support and fast deliver

Other AI Art Services I Offer