Browse categories
Explore
Fiverr Pro
English
$
USD
I will train a custom character lora for consistent ai images
Firiel
About this gig
I will train a custom Character LoRA based on your own character reference image(s), designed to keep the same identity across different poses, angles, outfits and scenes.
You will receive a ready-to-use .safetensors LoRA file that you can use in Stable Diffusion / ComfyUI workflows.
I create the training dataset myself from your character reference image(s), then train and test the LoRA. Additional tuning and broader testing are included in higher-tier packages.
My focus is character consistency and practical usability for comics, webtoons, visual novels, original characters and other creative projects.
The main product is the trained LoRA model the included AI images are test/preview renders only.
Please contact me before ordering if you are unsure whether your reference image(s) are suitable for LoRA training.
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.
AI Avatar Design disclosure
I understand that by acquiring AI Avatar Design services, I must abide by any and all disclaimer rules required by applicable laws and the platform(s) where this content will be posted. Read more about Fiverr’s AI Guidelines.
Get to know Firiel
Firiel
Custom Character LoRA Trainer and ComfyUI Specialist
- FromFrance
- Member sinceSep 2026
Languages
English
I train custom character LoRAs for creators who need consistent characters across different angles, poses, outfits and scenes.
I work with ComfyUI and deliver ready-to-use LoRA files for comics, webtoons, visual novels and original character projects. My focus is character consistency, clean training and practical results you can use in your own workflow.
FAQ
What do I need to provide for LoRA training?
You only need to provide at least one clear reference image of your character. I create the training dataset myself. Additional references are welcome if you want specific details to remain exact.
What will I receive?
You will receive the trained .safetensors LoRA file, plus the relevant trigger word/settings and test renders depending on the package.
Are the included AI images the main product?
No. The main product is the trained Character LoRA. The included images are only test renders used to demonstrate the model.
Can you train a LoRA from only one image?
Yes. I can start from one clear reference image and create the training dataset myself. If you have additional reference images, that is even better and can help preserve more character details accurately.
Can I use the LoRA in ComfyUI?
Yes. The LoRA is delivered as a .safetensors file and can be used in compatible Stable Diffusion / ComfyUI workflows.
