Instructions to use ProCreations/Image-2.1-Calibrated-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ProCreations/Image-2.1-Calibrated-FP8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ProCreations/Image-2.1-Calibrated-FP8", 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 on --image usage and multiple images support
#1
by shohanur-rahman01 - opened
Thanks for sharing this repo!
Could you clarify how the --image argument is used in the generate.py script? It would be helpful to have a short description or example in the help text/README. Also, is it possible to add support for inputting multiple images?
thanks for pointing this out! i've added editing examples and clearer help text. multiple references are now supported with --image first.png second.png or --image first.png --image second.png. refer to them as image 1 and image 2 in your prompt, in the order supplied. they jointly guide one output. single-image editing still works, and both multi-image formats have been tested. please update to the latest generate.py.