How to use erkam/sd-clevr-sg2im-objects_cap 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-2", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("erkam/sd-clevr-sg2im-objects_cap") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
These are LoRA adaption weights for stabilityai/stable-diffusion-2. The weights were fine-tuned on the erkam/clevr-with-depth-full-v2 dataset. You can find some example images in the following.
Base model
