Instructions to use SG161222/RealVisXL_V3.0_Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SG161222/RealVisXL_V3.0_Turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SG161222/RealVisXL_V3.0_Turbo", 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
Suggestions for my work
#1
by matemato - opened
Hello, I'm a big fan of your model and I plan to use it for my master thesis with some adjustments (with you permission of course). I really want the model to follow text with more detailed face descriptions (such as round face, high cheeks, narrow face etc.) which sadly fail on your model. For further work I plan to use a dataset with such descriptions. Do you have any suggestions as to how would I achieve the best results?
- By fine-tuning your model with detailed description dataset
- or merging your and a new model fine-tuned on this dataset?
Any suggestions as to how do you think it's best to tackle this problem is appreciated. Thank you for everything.