> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omnichar.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Supported models in Omnichar Studio

> The local models Omnichar Studio runs and trains, from Z-Image Turbo to MiniMax H3 and LTX-2.5, with VRAM needs and where to put the model files.

## Local models

| Model | Train | Generate | Trains on a 16GB card |
| - | - | - | - |
| FLUX.2 (klein Base 4B/9B) | yes | yes | yes, \~8.6GB |
| FLUX.1 dev (4-bit) | yes | yes | yes, \~10.4GB |
| Krea 2 (RAW, 4-bit) | yes | yes | yes, \~11.9GB |
| Z-Image Turbo | yes | yes | yes, \~13.4GB |
| MiniMax H3 (video, sound) | yes | yes | yes but slowly, \~12.7GB |
| LTX-2.5 (video, sound) | yes | yes | no, needs 48GB |
| Hosted models (fal) | no | yes | no GPU needed |

Those are training peaks at 512px. Training uses less VRAM than generating, and a LoRA trained at 512 applies at any generation resolution. The full benchmark matrix is in [TRAINING.md](https://github.com/omnichar/OmniChar/blob/main/TRAINING.md#benchmark-results).

* **Z-Image Turbo** is the low-VRAM place to start. It's distilled to run without CFG, so 1024×1024 fits in about 11.5GB.
* **Krea 2** is a 12.9B model with an undistilled RAW base and an 8-step Turbo build. Generating at 1024 peaks near 36GB, so plan on a 40GB card.
* **FLUX.2** takes several reference images, and the prompt addresses them by position. One node covers klein 4B and 9B, their Base builds, and dev.
* **MiniMax H3** generates video and its soundtrack in one pass: 24fps, 5 to 15 seconds. Plan on 64GB of system RAM.
* **LTX-2.5** is a 22B video-with-sound model: 24fps, 1 to 20 seconds. Each node has a Fast mode and a Quality mode. It's gated: accept the LTX-2 Community License on Hugging Face first.

## Get the model files

Each model node has a popup that downloads the diffusion model, VAE and text encoder, with visible progress. Nothing downloads in the background without you asking. To use files you already have, put them under `core/models/`:

```text theme={null}
core/models/
  diffusion_models/   the model's transformer
  text_encoders/      text encoders
  vae/                VAEs
  loras/              your trained adapters land here
  controlnet/         ControlNet and control-LoRA files
```

ComfyUI `int8_convrot` and `int8_tensorwise` files load unchanged and stay int8 in VRAM. A file the node can't read is listed with the reason.

## Hosted models

Add a Generate node and pick a model. The first provider is [fal](https://fal.ai): FLUX.2, GPT Image 2, Nano Banana, Seedance, MiniMax H3, LTX and more. Add your fal key in Settings. It stays on your machine, and you pay fal per render.

## Licences

Model weights carry their own licences. FLUX.2 klein 4B is Apache 2.0, while FLUX.2 dev, the 9B builds and FLUX.1 dev are non-commercial, and a LoRA trained on FLUX.1 dev inherits that. Krea 2, MiniMax H3 and LTX-2.5 have their own community licences. Check the licence on each model page before commercial use.


## Related topics

- [Omnichar Studio overview](/app/overview.md)
- [Install Omnichar Studio](/app/install.md)
- [Omnichar Studio command-line options](/app/command-line.md)
- [About Omnichar](/index.md)
- [Install the Omnichar ComfyUI node](/comfyui/install.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.