Instructions to use InstantX/SD3-Controlnet-Pose with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use InstantX/SD3-Controlnet-Pose with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("InstantX/SD3-Controlnet-Pose", 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
What are the minimum hardware specs (CPU/GPU/RAM/VRAM) for this model?
#8 opened about 1 year ago
by
yangSamoyed
I want the man's hand to go down and his head to go down in frustration where we don't see his face only his hair hanging down
1
#6 opened over 1 year ago
by
Sadya
Compatibility with DW Pose
#5 opened almost 2 years ago
by
spandit
Plans to release other resolutions?
#4 opened almost 2 years ago
by
mztk
Does this model's control image align with the original ControlNet-Openpose
#3 opened almost 2 years ago
by
citrinegui
Please ensure that the version of diffusers >= 0.30.0.dev0
1
#2 opened almost 2 years ago
by
Poukpalaova
Finger poses
#1 opened almost 2 years ago
by
ChristophSchuhmann