Instructions to use metercai/SimpleSDXL2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use metercai/SimpleSDXL2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("metercai/SimpleSDXL2", 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
Sharing the load with CPU or Shared GPU similar to Forge
#2
by Thangamani - opened
Very Good Effort - I appreciate.
Please alter the coding to share the image generation load between GPU, CPU and Shared GPU. (Reference: https://github.com/lllyasviel/stable-diffusion-webui-forge)
It will be useful for the users with low VRAM
I appreciate your efforts - But unable to use your SimpleSDXL2, I have only 8GB GPU
SimpleSDXL2 already supports the Flux models of bnb-nf4, bnb-nf4-v2, and gguf Qx series. Some users have successfully run Flux1 in the 4G VRAM environment. It can run on your 8GB GPU without any problems.
Thangamani changed discussion status to closed