Instructions to use ostris/Flex.1-alpha-Redux with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/Flex.1-alpha-Redux with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ostris/Flex.1-alpha-Redux", 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
Can we do something similar but pose transfer
#1
by ryg81 - opened
Hey Ostris,
I am a big fan of your work. Thanks for making things usable freely.
I just have an idea, not sure if possible to do. Can we create something similar for pose transfer, not the control net but redux like thing.
It should be possible assuming the vision encoder can understand the pose image. Though, something like a control lora would probably be quicker to train. Or when Flex.2 comes out, it will have built in pose input.
Looking forward to FLEX 2