Browse categories
Explore
Fiverr Pro
English
$
USD
I will train a custom character or style lora for sdxl and flux
Veribe
About this gig
Need a custom LoRA that keeps your character or visual style consistent across generations?
I will train and optimize a custom LoRA for Stable Diffusion, SDXL, or FLUX using your approved dataset.
This service can include:
- Character, person, product, or style LoRA training
- Dataset review, cleanup, and captioning
- Face, outfit, and identity consistency optimization
- Trigger words and recommended generation settings
- ComfyUI-ready .safetensors delivery
- Sample images for quality testing
You will receive:
- The trained LoRA model
- Preview images
- Recommended prompts, weights, and settings
- Clear usage guidance
Please message me before ordering if your dataset is large, inconsistent, or intended for a complex FLUX project. You must own or have permission to use all training images.
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 Veribe
Veribe
AI Image and ComfyUI Specialist
- FromBrazil
- Member sinceMay 2026
- Avg. response time21 hours
- Last delivery2 months
Languages
Portuguese, English, Spanish, Japanese
I specialize in custom AI image generation, LoRA training, image upscaling, restoration, and ComfyUI workflows for Stable Diffusion, SDXL, and FLUX.
I build practical solutions for consistent characters, portraits, concept art, ControlNet, IPAdapter, image-to-video, and optimized generation pipelines. I can also review datasets, improve captions, troubleshoot missing nodes and model errors, and optimize workflows for limited VRAM.
Every delivery focuses on clear instructions, reliable settings, and files that are ready to use in the buyer's workflow.
My Portfolio
Other AI Artists Services I Offer
FAQ
What models do you support?
I support Stable Diffusion 1.5, SDXL, FLUX, Pony, Illustrious, and anime-focused workflows.
Do you create NSFW LoRAs?
Yes. Both SFW and NSFW projects are supported.
Can you help with dataset preparation?
Yes. I can help with image selection, captioning, dataset cleanup, and optimization for better training results.
Will the LoRA work with ComfyUI?
Yes. I can provide guidance and compatibility recommendations for ComfyUI workflows.
Do you provide prompts and settings?
Yes. All packages include prompt recommendations and suggested generation settings.
Can you improve character consistency?
Yes. I focus heavily on facial consistency, body identity preservation, outfit consistency, and pose flexibility.
Do you support FLUX LoRA training?
Yes. I work with FLUX workflows and LoRA training pipelines.
What do I receive after delivery?
You will receive the trained LoRA file, sample images, and recommended prompts/settings for best results.
