Instructions to use glif/Gesture-Draw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use glif/Gesture-Draw 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/Gesture-Draw") prompt = "gstdrw style, figure mid dance, A dynamic gesture drawing featuring a figure mid-dance, rendered with confident yet delicate lines in fine charcoal on lightly textured, warm-gray paper. The strokes capture the fluid movement and expressive energy of the dancer, focusing on the essential gesture without becoming overly detailed. Subtle, soft smudges in the background suggest depth and atmosphere, allowing the figure to remain the focal point. The medium and paper's qualities complement the spontaneous, gestural nature of the subject." image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
- Xet hash:
- 96612ab61cb4ab2253fec3de04bf8b7465946878afcbf2df1fd3f88a16169b18
- Size of remote file:
- 451 MB
- SHA256:
- 4aa701c8ef8c937e57378624fc98713642817ee81b87e0845d02a4ab74b99e24
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.