Mila — Multi-Model Character LoRAs

Mila is a fictional AI character developed for consistent identity generation across multiple image and video model architectures.

This repository contains dedicated Mila LoRA weights for:

LTX-2.3 · Z-Image Turbo · Krea 2 Turbo

Each LoRA is trained specifically for its corresponding base model and should only be used with that architecture.

Prompt

Mila — realistic cafe portrait

Prompt

Mila — portrait on the Amalfi Coast

Prompt

Mila — Positano balcony video

Prompt

Mila — cafe lifestyle video

Prompt

Mila — grocery shopping video

Prompt

Mila — luxury car video

---

Model Overview

Model	Base Model	Trigger	LoRA Weight
LTX-2.3	Lightricks/LTX-2.3	mila	models/ltx-2.3/mila_ltx23_lora.safetensors
Z-Image Turbo	Tongyi-MAI/Z-Image-Turbo	mila_v1	models/z-image-turbo/mila_zimage_turbo_lora.safetensors
Krea 2 Turbo	krea/Krea-2-Turbo	mila	models/krea-2-turbo/mila_krea2_lora.safetensors

---

LTX-2.3

Character Video LoRA

Base Model: Lightricks/LTX-2.3
Trigger: mila
Recommended LoRA Strength: 0.8
Training Steps: 2000

The LTX-2.3 version is designed for realistic character-focused video generation while maintaining Mila's facial identity across motion, expressions, environments and camera compositions.

It works particularly well for:

• Lifestyle videos
• Fashion content
• Travel scenes
• Social media
• Reels-style shots
• Fitness scenes
• Luxury environments
• Natural facial expressions
• Cinematic character shots

Example Prompt

mila, consistent facial identity, blonde ponytail,
soft facial features, expressive eyes, natural skin texture,
cream outfit, luxury coastal background, warm sunlight,
realistic cinematic lifestyle video, natural movement

---

Z-Image Turbo

Character Image LoRA

Base Model: Tongyi-MAI/Z-Image-Turbo
Trigger: mila_v1
Training Steps: 2000

The Z-Image Turbo version focuses on high-quality realistic still images while maintaining Mila's recognizable facial identity.

Recommended use cases include:

• Portrait photography
• Lifestyle imagery
• Fashion
• Luxury environments
• Travel photography
• Social media content
• Full-body character shots
• Cinematic portraits

Example Prompt

mila_v1, blonde ponytail, soft facial features,
expressive eyes, natural skin texture,
premium lifestyle photography,
warm natural sunlight, realistic skin detail,
cinematic photography

---

Krea 2 Turbo

Character Image LoRA

Base Model: krea/Krea-2-Turbo
Trigger: mila

The Krea 2 Turbo version is designed for high-quality character rendering with emphasis on natural photography, skin detail, fashion imagery and premium cinematic aesthetics.

Recommended use cases include:

• Photorealistic portraits
• Fashion photography
• Editorial imagery
• Lifestyle scenes
• Travel content
• Luxury environments
• Full-body compositions

Example Prompt

mila, blonde woman, soft facial features,
expressive eyes, natural skin texture,
premium fashion photography,
warm cinematic daylight,
realistic lifestyle aesthetic

---

About Mila

Mila is a fictional AI-generated character.

The project explores consistent character identity across independent generative model architectures while preserving flexibility in:

• Clothing
• Hairstyle
• Pose
• Expression
• Environment
• Lighting
• Camera framing
• Image and video generation

Rather than locking the character to a single scene or aesthetic, the LoRAs are intended to preserve Mila's recognizable identity across a wide range of realistic scenarios.

---

Licensing

This repository contains LoRA adapters trained for multiple independent base-model families.

Use and redistribution of each LoRA must comply with the license and usage terms of its corresponding base model:

• Lightricks/LTX-2.3
• Tongyi-MAI/Z-Image-Turbo
• krea/Krea-2-Turbo

Please review the original base-model licenses before redistribution, deployment or commercial use.

---

SOLRICKS

Generative AI · Models · Workflows · Tools

Built for experimentation with high-quality image and video generation.