Text-to-Image
Diffusers
English
Text-to-Image
IP-Adapter
Flux.1-dev
image-generation
Stable Diffusion
Instructions to use InstantX/FLUX.1-dev-IP-Adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use InstantX/FLUX.1-dev-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("InstantX/FLUX.1-dev-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
If and let this iPadapter only play the role of maintaining the IP role image, does this require a new model?
#10
by ss996 - opened
If this model is only used to maintain the IP character image, does this require a new model? I have done a lot of testing and this model does not seem to be trained for this
We need, for example, Naruto Swirl can maintain well in different styles and different scenes. This may not be a real face, but an anime-style face.
How should this be done?Can someone answer?