Instructions to use glif/how2draw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use glif/how2draw with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("glif/how2draw") prompt = "an owl, How3Draw" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
generation parameters
#4
by vatsal2473 - opened
This is a really great model !, if possible can you please provide the generation parameters like number of steps, sample, lora strength, etc or maybe comfyui workflow for this because i was not able to replicate the same results
hey!
You can check the source of the glif for defaults:
https://glif.app/@Ampp/glifs/cm0zpqvq2000lqe5lyjkw4qe5
It seems the defaults are:
Thank a lot bro, that worked !
rvorias changed discussion status to closed
