Instructions to use multimodalart/sd-fine-tunable with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use multimodalart/sd-fine-tunable with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("multimodalart/sd-fine-tunable", 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
- Draw Things
- DiffusionBee
More info / documentation needed
#3
by johnslegers - opened
So, what exactly is different between this model and the default model?
How does this impact Dreambooth training?
Does the config also impact the ShivamShrirao version or the Joe Penna version of Dreambooth scripts out there?
Can I just copy affected config to my own models to achieve the same?