Instructions to use phil329/face_lora_sd15 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use phil329/face_lora_sd15 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("phil329/face_lora_sd15") prompt = "A young woman with smile, wearing a purple hat." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Prompt for fine-tuning.
#1
by debadas - opened
How do you generate the prompts used for the fine-tuning ?
We get the simple text prompts by using the llava1.5-7B model, which is similar to the operation in ConsistentID(https://arxiv.org/pdf/2404.16771).
Would you be able share the prompts and corresponding images ?
We have uploaded the captions of FFHQ and CelebA-HQ datasets.
phil329 changed discussion status to closed