I will train custom lora for qwen wan 2x consistent character


About this gig
Hi!
Want perfect character/style consistency in your AI generations?
I train high-quality custom LoRAs using reliable Apache-licensed bases: Qwen, z-Image & Wan 2.x ideal for repeatable characters in digital art, branding, games, social media projects (SFW only).
What you get:
Professional .safetensors LoRA file
Optimized trigger words & effective prompts
10-40+ high-quality test generations
Clear training guide & usage tips
Optional ComfyUI workflow snippets (Premium)
Process:
- Send 10-50+ reference images + detailed description or let them create! There for take a look at my other gig!
- I prepare dataset & train (high consistency focus)
- Review initial samples revisions
- Final delivery + instructions
Results depend on dataset quality better input = better output.
All trainings SFW & ethical.
Check my previous work on Civitai: https://civitai.com/user/nova969
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 Andreas B.
Expert for AI Content Creation
- FromGermany
- Member sinceJan 2026
Languages
German, English
FAQ
How many images do I need?
10–20 minimum for Basic, 30+ recommended for best results.
Can I get NSFW?
Sorry, strictly SFW only.
How long?
Basic 5 days, Standard/Premium 3 days (rush extra available)

