How to use backnotprop/crash-report-framed 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("backnotprop/crash-report-framed") prompt = "a close up of a colorful circular object with a city in the background in the style of <s0><s1>, explosion of data fragments, isolated on white background, dendrites, 3d cell shaded, london, view from slightly above, atsmospheric, looking partly to the left, fully symmetrical, giant explosion, datamoshed" image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!