|
|
--- |
|
|
base_model: HiDream-ai/HiDream-I1-Full |
|
|
library_name: diffusers |
|
|
license: mit |
|
|
instance_prompt: a photo of sks dog |
|
|
widget: [] |
|
|
tags: |
|
|
- text-to-image |
|
|
- diffusers-training |
|
|
- diffusers |
|
|
- lora |
|
|
- hidream |
|
|
- hidream-diffusers |
|
|
- template:sd-lora |
|
|
- 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/dog-hidream-lora |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
## Model description |
|
|
|
|
|
These are linoyts/dog-hidream-lora 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 `a photo of sks dog` to trigger the image generation. |
|
|
|
|
|
## Download model |
|
|
|
|
|
[Download the *.safetensors LoRA](linoyts/dog-hidream-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 UniPCMultistepScheduler, HiDreamImagePipeline |
|
|
|
|
|
>>> scheduler = UniPCMultistepScheduler( |
|
|
... flow_shift=3.0, prediction_type="flow_prediction", use_flow_sigmas=True |
|
|
... ) |
|
|
|
|
|
>>> 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/dog-hidream-lora") |
|
|
>>> image = pipe(f"a photo of sks dog").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) |
|
|
|
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
#### How to use |
|
|
|
|
|
```python |
|
|
# TODO: add an example code snippet for running this diffusion pipeline |
|
|
``` |
|
|
|
|
|
#### Limitations and bias |
|
|
|
|
|
[TODO: provide examples of latent issues and potential remediations] |
|
|
|
|
|
## Training details |
|
|
|
|
|
[TODO: describe the data used to train the model] |
