Instructions to use logo-wizard/logo-diffusion-checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use logo-wizard/logo-diffusion-checkpoint with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("logo-wizard/logo-diffusion-checkpoint") 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
Possible to make a *.ckpt or *.safe-tensors file available?
#2
by joelclimbsthings - opened
I'd love to try this model, although I'm inexperienced in working directly with a diffusers directory structure--is it possible to add a CKPT or something similar?
If not, is using something like this script what I need to do?
Yes, you can just use this script for your purposes. First you need git clone this repo. Then call the script using bash: convert_diffusers_to_original_stable_diffusion.py --model_path path_to_cloned_repo --checkpoint_path path_to_save_model --half