| --- |
| license: other |
| base_model: |
| - Lightricks/LTX-2.3 |
| - Tongyi-MAI/Z-Image-Turbo |
| - krea/Krea-2-Turbo |
| tags: |
| - lora |
| - character |
| - character |
| - consistency |
| - mila |
| - ltx-2.3 |
| - z-image-turbo |
| - krea-2-turbo |
| - text-to-image |
| - text-to-video |
| - image-to-video |
| - realistic |
| - cinematic |
| - fashion |
| - lifestyle |
| widget: |
| - text: Mila — realistic cafe portrait |
| output: |
| url: models/z-image-turbo/mila-cafe-portrait.png |
| - text: Mila — portrait on the Amalfi Coast |
| output: |
| url: models/z-image-turbo/mila-amalfi-coast.png |
| - text: Mila — Positano balcony video |
| output: |
| url: models/ltx-2.3/mila-positano-balcony.mp4 |
| - text: Mila — cafe lifestyle video |
| output: |
| url: models/ltx-2.3/mila-cafe-lifestyle.mp4 |
| - text: Mila — grocery shopping video |
| output: |
| url: models/ltx-2.3/mila-grocery-shopping.mp4 |
| - text: Mila — luxury car video |
| output: |
| url: models/ltx-2.3/mila-luxury-car.mp4 |
| pipeline_tag: text-to-video |
| --- |
| |
| # 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. |
|
|
| <Gallery /> |
|
|
| --- |
|
|
| ## 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 |
|
|
| ```text |
| 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 |
|
|
| ```text |
| 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 |
|
|
| ```text |
| 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. |
