Instructions to use joachimsallstrom/aether-cloud-lora-for-sdxl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use joachimsallstrom/aether-cloud-lora-for-sdxl with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("joachimsallstrom/aether-cloud-lora-for-sdxl") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
YAML Metadata Error:"widget[0].text" must be a string
Aether Cloud - LoRA for SDXL
This is Aether Cloud - a cloud based subject and object LoRA trained on animals, people and some other stuff. Play with weights but 1 is a good base. Higher and you seem to get more clouds - lower and you get more distinct features. Works well with no negative prompting for basic things. Make sure to check out prompt examples with the images in this gallery.
Thanks to ThinkDiffusion for letting me test on their platform!
ImaginAir!
Image examples for the model:
- Downloads last month
- 53
Model tree for joachimsallstrom/aether-cloud-lora-for-sdxl
Base model
stabilityai/stable-diffusion-xl-base-1.0








