Instructions to use jasperai/flash-sd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jasperai/flash-sd 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("jasperai/flash-sd") 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
misunderstanding of correct parameters for generation in A1111
#3
by 4eJIoBek - opened
I think it works only on the trained model. It guess it targets the block weights of the model specifically.
Again, not an expert... just a shot in the dark here.
Edit 1 : its not working at all
Edit 2: managed to make it work, the provided here are the weights to use for training. If you still interested to try it out, I uploaded a model card. shehabelkadi/Flash-SD-Lora
