---
base_model: HiDream-ai/HiDream-I1-Full
library_name: diffusers
license: mit
instance_prompt: a dog, yarn art style
widget: []
tags:
- text-to-image
- diffusers-training
- diffusers
- lora
- hidream
- hidream-diffusers
- template:sd-lora
---

<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->


# HiDream Image DreamBooth LoRA - linoyts/HiDream-yarn-art-LoRA

<Gallery />

## Model description

These are linoyts/dog-hidream-lora-offload-mini-test DreamBooth LoRA weights for HiDream-ai/HiDream-I1-Full.

The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [HiDream Image diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_hidream.md).

## Trigger words

You should use `yarn art style` to trigger the image generation.

## Download model

[Download the *.safetensors LoRA](https://huggingface.co/linoyts/HiDream-yarn-art-LoRA/tree/main) in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
    >>> import torch
    >>> from transformers import PreTrainedTokenizerFast, LlamaForCausalLM
    >>> from diffusers import HiDreamImagePipeline

    >>> tokenizer_4 = PreTrainedTokenizerFast.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
    >>> text_encoder_4 = LlamaForCausalLM.from_pretrained(
    ...     "meta-llama/Meta-Llama-3.1-8B-Instruct",
    ...     output_hidden_states=True,
    ...     output_attentions=True,
    ...     torch_dtype=torch.bfloat16,
    ... )

    >>> pipe = HiDreamImagePipeline.from_pretrained(
    ...     "HiDream-ai/HiDream-I1-Full",
    ...     scheduler=scheduler,
    ...     tokenizer_4=tokenizer_4,
    ...     text_encoder_4=text_encoder_4,
    ...     torch_dtype=torch.bfloat16,
    ... )
    >>> pipe.enable_model_cpu_offload()
    >>> pipe.load_lora_weights(f"linoyts/HiDream-yarn-art-LoRA")
    >>> image = pipe(f"yoda, yarn art style").images[0]


```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)