Text-to-Image
Diffusers
Safetensors
English
StableDiffusionXLPipeline
stable-diffusion
stable-diffusion-xl
Instructions to use Raelina/Rae-Diffusion-XL-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Raelina/Rae-Diffusion-XL-V2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Raelina/Rae-Diffusion-XL-V2", 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
Maybe model is broken?
#1
by John6666 - opened
Thanks for the great model.
I especially deeply appreciate to support Yuru Yuri. โบ
BTW, I got the following warning in the Toolkit of the SD WebUI. Maybe the model file is broken. Civitai's file, too.
I could generate an image, though?
Model is 6.46 GB. Model type identified as VAE-v1-BROKEN. Model components are: VAE-v1-SD.
Contains 6.31 GB of junk data!
Model will be pruned to 159.56 MB.
Thanks for the kind words! I'm glad you're enjoying the model and supporting Yuru Yuri. ๐
Regarding the warning in the Toolkit of the SD WebUI, it's because I'm using the SDXL VAE by Madebyollin https://huggingface.co/madebyollin/sdxl-vae-fp16-fix . This is a fixed version of the official SDXL VAE, which supports FP16, as the official SDXL VAE doesn't support FP16. Despite the warning, you should still be able to generate images without any issues.
I'm glad to hear that there are no problems. Sorry for the trouble.
Thank you!๐
John6666 changed discussion status to closed