Instructions to use sanjeevnara/stablethumbs-dreambooth-multiconcept with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use sanjeevnara/stablethumbs-dreambooth-multiconcept with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("sanjeevnara/stablethumbs-dreambooth-multiconcept", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Stable Diffusion v1.5 trained using Dreambooth approach to generate 'thumbs-up' style images. Also trained to generate professional Soccer player Vinicius Jr.'s face.
Prompt Guide:
- For a thumbs up style, add 'with a thumbs up' or 'thumbs up gesture' to your prompt e.g.
'photo of Messi with a thumbs up gesture, high quality'. - For Vinicius Jr, add the rare token 'xjy' e.g.
'photo of xjy with a thumbs up gesture, high quality'.
Uses Diffusers library / StableDiffusionPipeline.
- Downloads last month
- -