Create app.py

app.py

@@ -0,0 +1,23 @@
+import torch
+
+from diffusers import UniDiffuserPipeline
+from diffusers.utils import load_image
+
+device = "cuda"
+model_id_or_path = "thu-ml/unidiffuser-v1"
+pipe = UniDiffuserPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float16)
+pipe.to(device)
+
+# Image variation can be performed with an image-to-text generation followed by a text-to-image generation:
+# 1. Image-to-text generation
+image_url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/unidiffuser/unidiffuser_example_image.jpg"
+init_image = load_image(image_url).resize((512, 512))
+
+sample = pipe(image=init_image, num_inference_steps=20, guidance_scale=8.0)
+i2t_text = sample.text[0]
+print(i2t_text)
+
+# 2. Text-to-image generation
+sample = pipe(prompt=i2t_text, num_inference_steps=20, guidance_scale=8.0)
+final_image = sample.images[0]
+final_image.save("unidiffuser_image_variation_sample.png")