Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
iamxenos
stable-diffusion
stable-diffusion-diffusers
Instructions to use Yntec/XenoGASM-MK2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Yntec/XenoGASM-MK2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Yntec/XenoGASM-MK2", 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
Fixed error: 'Attention' object has no attribute 'to_to_k'
#2
by Yntec - opened
I'm including this information here in case you face this error, more information here: https://github.com/easydiffusion/easydiffusion/issues/1618
First you have to upload the model into a repo, then use a space like this one:
https://huggingface.co/spaces/John6666/sd-to-diffusers-v2
To create a new repo with the diffusers version (I recommend unticking half-precision and ticking no-ema in advanced options). Then you convert back to single safetensors in a space like this:
https://huggingface.co/spaces/Yntec/diffusers-to-sd
That's the secret that makes it work:
You can now download a fully working model from there and any merge with this model will not inherit the error!
