I will train a custom lora for ai image model with comfyui workflow

B
blahblahpopcorn
B
blahblahpopcorn
Blahblah
train a custom lora for ai image model with comfyui workflow
Full Screen
train a custom lora for ai image model with comfyui workflow
Full Screen
Full Screen
train a custom lora for ai image model with comfyui workflowtrain a custom lora for ai image model with comfyui workflowtrain a custom lora for ai image model with comfyui workflow

About this gig

I handle dataset prep, captioning, training, and a clean sample pack. 24-72h delivery depending on tier.


Message me before ordering if you need a custom scope or NSFW work.and ship them with a ready-to-run ComfyUI workflow.


WHY ME

  • IT + ML background, not a hobbyist one-click trainer
  • - ComfyUI native: custom node graphs, upscalers, face-fix pipelines
  • - Multi-model fluency across Flux, SDXL, SD3, Pony, Wan, Qwen
  • - Clean dataset curation = consistent results, no morphing faces

  • WHAT YOU GET
  • - Trained .safetensors LoRA file
  • - Optimized trigger words + recommended weights
  • - Sample generation pack (PNG)
  • - ComfyUI workflow JSON ready to load
  • - Quick-start usage notes (PDF)

  • PERFECT FOR
  • - AI influencers / virtual models
  • - Brand product consistency
  • - Characters / IP for games & comics
  • - Signature art-style replication
  • - E-com lookbooks & ad creative

  • Send me 10-25 reference images and a short description. Need a custom LoRA that nails your character, product, or art style across every generation? I train production-grade LoRAs for Flux (dev / Schnell / Pro / FLUX.2), SDXL, SD3, and Pony

  • Model expertise

    • Flux

  • Output type

    • Image

  • Purpose

    • Image generation
    • Image manipulation
    • Visual effects
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 Blahblah

Blahblah
  • FromUnited States
  • Member sinceNov 2018
  • Avg. response time1 hour

  • Languages

    English
I build custom LoRA models trained on your character for consistent. I handle the full pipeline: dataset curation, image cleaning and tagging, structural organization, training, and testing. The result is a LoRA that produces the character you expect, consistently. What I deliver: Custom curated and tagged image datasets (50–100+ images) Trained LoRA model on your choice of base Test outputs to verify consistency Full working pipeline documentation Compatible with: ComfyUI, AUTOMATIC1111, and standard Stable Diffusion workflows. Models I work with: SDXL, SD 1.5, Pony, Flux, NanoBanana, Kling.

Related tags