Norod78/Rubber-Duck-blip-captions
Viewer • Updated • 165 • 14 • 2
How to use Norod78/SD15-Rubber-Duck-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Norod78/SD15-Rubber-Duck-LoRA")
prompt = "Wonderwoman Rubber duck"
image = pipe(prompt).images[0]


(CivitAI)
While SDXL is really good at out-of-the box generation of rubber ducks, SDv1.5 needs a little LoRA help. So here it is.
Use "Rubber duck" in your prompts.
You should use Rubber duck to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Norod78/rubber-duck-sd1-5', weight_name='Rubber_Duck_SD1.5-000009.safetensors')
image = pipeline('`Rubber duck`').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
Base model
runwayml/stable-diffusion-v1-5