diffusers/pr_12249/en/using-diffusers/automodel.md

# AutoModel

The [AutoModel](/docs/diffusers/pr_12249/en/api/models/auto_model#diffusers.AutoModel) class automatically detects and loads the correct model class (UNet, transformer, VAE) from a `config.json` file. You don't need to know the specific model class name ahead of time. It supports data types and device placement, and works across model types and libraries.

The example below loads a transformer from Diffusers and a text encoder from Transformers. Use the `subfolder` parameter to specify where to load the `config.json` file from.

```py
import torch
from diffusers import AutoModel, DiffusionPipeline

transformer = AutoModel.from_pretrained(
    "Qwen/Qwen-Image", subfolder="transformer", torch_dtype=torch.bfloat16, device_map="cuda"
)

text_encoder = AutoModel.from_pretrained(
    "Qwen/Qwen-Image", subfolder="text_encoder", torch_dtype=torch.bfloat16, device_map="cuda"
)
```

[AutoModel](/docs/diffusers/pr_12249/en/api/models/auto_model#diffusers.AutoModel) also loads models from the [Hub](https://huggingface.co/models) that aren't included in Diffusers. Set `trust_remote_code=True` in [AutoModel.from_pretrained()](/docs/diffusers/pr_12249/en/api/models/auto_model#diffusers.AutoModel.from_pretrained) to load custom models.

```py
import torch
from diffusers import AutoModel

transformer = AutoModel.from_pretrained(
    "custom/custom-transformer-model", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="cuda"
)
```

If the custom model inherits from the [ModelMixin](/docs/diffusers/pr_12249/en/api/models/overview#diffusers.ModelMixin) class, it gets access to the same features as Diffusers model classes, like [regional compilation](../optimization/fp16#regional-compilation) and [group offloading](../optimization/memory#group-offloading).

> [!NOTE]
> Learn more about implementing custom models in the [Community components](../using-diffusers/custom_pipeline_overview#community-components) guide.