Instructions to use h94/IP-Adapter-FaceID with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use h94/IP-Adapter-FaceID 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-FaceID", 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 Settings
- Draw Things
- DiffusionBee
Question: edge/mobile deployment viability?
#75
by 3morixd - opened
We evaluate every interesting model for mobile deployment on our 40-phone farm (Snapdragon 865).
Question: has anyone tested this model on mobile/edge devices? What are the key constraints (size, speed, memory)?
Our criteria: <2GB after Q4_K_M, >10 t/s generation, >2GB RAM free.
Would love to hear from anyone with mobile experience.
- Dispatch AI (FZE), Sharjah UAE