Thanks for your image-to-image variation work. I am running a simple demo with your sample code and getting some errors. I tried to find the file but I am unable to find it. What is the origin of StableDiffusionImageVariationPipeline file?
from PIL import Image
from diffusers import StableDiffusionImageVariationPipeline
device = "cuda:0"
sd_pipe = StableDiffusionImageVariationPipeline.from_pretrained(
"lambdalabs/sd-image-variations-diffusers",
revision="v2.0",
)
sd_pipe = sd_pipe.to(device)
im = Image.open("/home/cvpr/Desktop/bird.jpg")
tform = transforms.Compose([
transforms.ToTensor(),
transforms.Resize(
(224, 224),
interpolation=transforms.InterpolationMode.BICUBIC,
antialias=False,
),
transforms.Normalize(
[0.48145466, 0.4578275, 0.40821073],
[0.26862954, 0.26130258, 0.27577711]),
])
inp = tform(im).to(device)
out = sd_pipe(inp, guidance_scale=3)
out["images"][0].save("result.jpg")
from diffusers import StableDiffusionImageVariationPipeline
ImportError: cannot import name 'StableDiffusionImageVariationPipeline' from 'diffusers' (/media/cvpr/CM_1/lambda-diffusers/.venv/lib/python3.8/site-packages/diffusers/__init__.py)
Dear @eolecvk @justinpinkney @chuanli11 @osanseviero
Thanks for your image-to-image variation work. I am running a simple demo with your sample code and getting some errors. I tried to find the file but I am unable to find it. What is the origin of
StableDiffusionImageVariationPipelinefile?Traceback