Upwork home
Sign up
Project Catalog
DesignDesign
Video & AudioVideo & Audio
Development & ITDevelopment & IT
MarketingMarketing
Writing & TranslationWriting & Translation
MoreMore

You will get Custom AI Character LoRA Training

Sofia C.Status: Offline
Sofia C.
Preview imagePreview image

Let a pro handle the details

Buy Generative AI services from Sofia, priced and ready to go.
Sofia C.Status: Offline
Sofia C.
Preview imagePreview image

Let a pro handle the details

Buy Generative AI services from Sofia, priced and ready to go.

Project details

I train custom LoRA models from scratch for brand characters,
AI influencers, and product consistency pipelines. My process
covers dataset curation, captioning, full training configuration
on Flux Dev, checkpoint evaluation, and delivery of a
ComfyUI-ready .safetensors file.

I come from an Art Direction for Film and TV background, which
means I approach every LoRA with visual consistency and creative
direction in mind. I think in terms
of lighting, camera angle, and character logic, so the model I
deliver actually performs across scenes.

Every LoRA is trained specifically for your use case: AI
influencer, brand character, product shots, or ad content.
AI Algorithms
Convolutional Neural Network, Generative Adversarial Network, Transformer Model, Variational Autoencoder
AI Applications
AI Content Creation, AI Text-to-Speech, AI-Generated Art, AI-Generated Video, Image Processing, Image-to-Image Translation, Neural Style Transfer, Synthetic Data Generation
AI Development Language
Python
AI Tools
Hugging Face
AI Models
Stable Diffusion
What's included
Service Tiers Starter
$250
Standard
$450
Advanced
$750
Delivery Time 5 days 10 days 14 days
Number of Revisions
123
AI Model Integration
-
-
-
Batch Normalization
-
-
-
Database Integration
-
-
-
Detailed Code Comments
-
-
-
Image Upscaling
-
MLOps
-
-
-
Model Deployment
-
-
-
Model Documentation
-
-
Model Monitoring
-
-
-
Model Testing & Optimization
-
Model Tuning
Natural Language Processing
-
-
-
NLP Tokenization
-
-
-
Pre-Training
-
-
-
Prompt Engineering
Setup File
Source Code
-
-
-
Optional add-ons You can add these on the next page.
Additional Revision
+$25

Frequently asked questions

Sofia C.Status: Offline

About Sofia

Sofia C.Status: Offline
AI Creative Strategist for DTC Brands - ComfyUI - Flux - LoRA
Buenos Aires, Argentina - 8:05 pm local time
I direct end-to-end AI video and image campaigns for brands and creative agencies: from ComfyUI/Flux pipelines and custom LoRA training to ElevenLabs voice production and final cut in Premiere Pro. 7+ years across digital production, electronic arts and generative content; based in Buenos Aires (UTC-3, full overlap with US Eastern).

I'm a Creative Technologist and multidisciplinary artist working at the intersection of body, technology, and moving image. My work is about making the invisible visible whether that's translating a heartbeat into light, building AI-generated character pipelines, or directing live visual performances for 10,000+ audiences.

I bring 7+ years producing and directing across digital media, electronic arts, and AI-driven content. My background spans the full creative pipeline: concept → production → post → live execution.

What I actually do: — AI Video & Generative Workflows: I run ComfyUI pipelines for rapid prototyping, LoRA training, and character asset generation. Fluent in Higgsfield, Premiere, and Photoshop. — Live A/V Direction: Real-time VJing (Resolume Arena), CCTV integration, hybrid analog/digital video systems. — Physical Computing & Interactive Installations: Biosensor systems (ESP32/Arduino), motion detection interfaces (Processing/Python), OSC/MIDI synchronization. — Production & Project Management: Grant writing and execution (public funding), international festival programming, cross-cultural team coordination (EN/FR/ES).

My work has been recognized internationally — BFI London, Eye Filmmuseum Amsterdam, Cinedans, Naves Matadero — and awarded at the ISCA (International Student Creative Awards, Japan) and the NOWNESS × Cinedans Pitch Lab.

Currently studying Electronic Arts (B.A., UNTREF) and open to remote opportunities with digital media, AI platforms, and creative production teams globally.

Steps for completing your project

After purchasing the project, send requirements so Sofia can start the project.

Delivery time starts when Sofia receives requirements from you.

Sofia works on your project following the steps below.

Revisions may occur after the delivery date.

Review and preparation

I review your dataset and prepare images for training: cropping, captioning, and quality check.

LoRA training

I run the LoRA training on Flux Dev with optimized parameters for your character and use case.

Review the work, release payment, and leave feedback to Sofia.