How to use kviai/Paint-Diffuion-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("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("kviai/Paint-Diffuion-V2") prompt = "darth vader fighting superman, 2 people, lightsaber" image = pipe(prompt).images[0]
Paint diffusion is fine tune model from stabilityai/stable-diffusion-xl-base-1.0. It generates images like watercolor paintings.
Base model
