sd image variations diffusers EU AI Act Compliance Profile

Stable Diffusion Image Variations Model Card

📣 V2 model released, and blurriness issues fixed! 📣

🧨🎉 Image Variations is now natively supported in 🤗 Diffusers! 🎉🧨

Version 2

This version of Stable Diffusion has been fine tuned from CompVis/stable-diffusion-v1-4-original to accept CLIP image embedding rather than text embeddings. This allows the creation of "image variations" similar to DALLE-2 using Stable Diffusion. This version of the weights has been ported to huggingface Diffusers, to use this with the Diffusers library requires the Lambda Diffusers repo.

This model was trained in two stages and longer than the original variations model and gives better image quality and better CLIP rated similarity compared to the original version

See training details and v1 vs v2 comparison below.

Example

Make sure you are using a version of Diffusers >=0.8.0 (for older version see the old instructions at the bottom of this model card)

from diffusers import StableDiffusionImageVariationPipeline
from PIL import Image

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("path/to/image.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).unsqueeze(0)

out = sd_pipe(inp, guidance_scale=3)
out["images"][0].save("result.jpg")

The importance of resizing correctly... (or not)

Note that due a bit of

Your obligations as a sd image variations diffusers deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library