tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: A young woman with smile, wearing a purple hat.
parameters:
negative_prompt: >-
worst quality, low quality, bad anatomy, watermark, text, blurry,
cartoon, unreal
output:
url: images/output.png
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: null
license: mit
pytorch_lora_weights.safetensors
- Prompt
- A young woman with smile, wearing a purple hat.
- Negative Prompt
- worst quality, low quality, bad anatomy, watermark, text, blurry, cartoon, unreal
Model description
This model is a fine-tuned version of the Stable Diffusion architecture, leveraging the Low-Rank Adaptation (LoRA) technique. It has been trained using the CelebA-HQ and FFHQ datasets, both renowned for their high-quality images of human faces.
Training Details:
- Base Model: Stable Diffusion
- Adaptation Technique: Low-Rank Adaptation (LoRA)
- Datasets: CelebA-HQ (30,000 images), FFHQ (70,000 images)
- Resolution: resolution : 512*512 fine-tuning for detailed facial synthesis
Example Usages:
```python
import torch from diffusers import StableDiffusionPipeline,UNet2DConditionModel
pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5").to("cuda")
pipeline.load_lora_weights("phil329/face_lora_sd15", weight_name="pytorch_lora_weights.safetensors")
text = 'A young woman with smile, wearing a purple hat.' lora_image = pipeline(text).images[0]
display(lora_image)
```
Results
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.