Instructions to use h94/IP-Adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use h94/IP-Adapter with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("h94/IP-Adapter", 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
- Local Apps
- Draw Things
- DiffusionBee
IP-Adapter for PonyXL
#31
by snusnumrik - opened
Many models that work SDXL work poorly on PonyXL, since it is a heavily finteuned version of SDXL,
I was unable to get acceptable results on face IP-Adapter with PonyXL.
Is it possible to release a IP Adapter for PonyDiffusionXL ?
Or I just need to improve my workflow?
I've been asking for the same thing. Haven't found it yet. The SDXL IP-Adapters don't play nice. I'm sure it's just a bit of tweaking to get it done.
I discovered that there is an ControlNet model called anytest that works very well with pony. Much better than many others. Highly reccomend