Mila is a fictional character LoRA designed for consistent character generation across LTX-2.3 text-to-video and Z-Image Turbo text-to-image workflows.
Mila works especially well for realistic lifestyle content, fashion scenes, luxury environments, social media content, outdoors, fitness, travel, and cinematic character shots.
Both versions are trained specifically for their respective image and video generation workflows.
Triggers:
• LTX-2.3: mila or mila_v1
• Z-Image Turbo: mila_v1
• Krea-2 Turbo: mila_v1
Recommended use cases:
• Consistent fictional character generation
• Realistic character video generation
• Portrait and lifestyle photography
• Fashion, luxury, fitness, travel, and social media content
• Luxury hotel interior and exterior cinematic scenes
• Stable facial identity across different outfits, poses, and locations
Description
Z-Image Turbo version of the Mila character LoRA.
Trained character LoRA for realistic portrait, medium-shot and full-body generation.
Trigger: mila_v1
Recommended strength: 0.85
Sampler: Euler
Trained at 832 / 1472 resolution with Rank 32 for 1750 steps.
For best character consistency, include mila_v1 near the beginning of the prompt. Works well for realistic photography, lifestyle, fashion and cinematic portrait generation.
Note: If you generate images here, please use the Z-Image Turbo model.
https://civitai.com/models/2168935/z-image-turbo?modelVersionId=2442439
FAQ
Details
Downloads
91
Platform
CivitAI
Platform Status
Available
Created
7/29/2026
Updated
8/9/2026
Deleted
-
Trigger Words:
mila_v1