Instructions to use rain1011/pyramid-flow-sd3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use rain1011/pyramid-flow-sd3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("rain1011/pyramid-flow-sd3", torch_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
How is it MIT?
#6
by ostris - opened
This is a finetune of SD3 medium, so how it is MIT licensed? It should inherit the SD3 license as it is a derivative work right?
Thanks for your reminding, we did not notice the license problem at first. We will modify the license of the SD3 initialized weight. In the meantime, we commit to releasing the next model checkpoint trained from scratch under the MIT license.
We have updated the LICENSE
rain1011 changed discussion status to closed