init

app.py

@@ -0,0 +1,46 @@
+import gradio as gr
+import os
+
+import torch
+from diffusers import AutoencoderTiny
+from torchvision.transforms.functional import to_pil_image, center_crop, resize, to_tensor
+
+device = 'cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu'
+d_type = torch.float32 if device == 'mps' else torch.float16
+
+model_id = "madebyollin/taesd"
+vae = AutoencoderTiny.from_pretrained(model_id, safetensors=True, torch_dtype=d_type).to(device)
+
+
+@torch.no_grad()
+def decode(image):
+    t = to_tensor(image).unsqueeze(0).to(device, dtype=d_type)
+    unscaled_t = vae.unscale_latents(t)
+    reconstructed = vae.decoder(unscaled_t).clamp(0, 1)
+    return to_pil_image(reconstructed[0])
+
+
+astronaut = os.path.join(os.path.dirname(__file__), "images/21.encoded.png")
+
+
+def app():
+    return gr.Interface(decode,
+                        gr.Image(type="pil",
+                                 image_mode="RGBA",
+                                 mirror_webcam=False,
+                                 label='64x64',
+                                 value=astronaut),
+                        gr.Image(type="pil",
+                                 image_mode="RGB",
+                                 label='512x512',
+                                 height=256,
+                                 width=256
+                                 ),
+                        examples=[
+                            os.path.join(os.path.dirname(__file__), "images/18.encoded.png"),
+                            os.path.join(os.path.dirname(__file__), "images/20.encoded.png")
+                        ])
+
+
+if __name__ == "__main__":
+    app().launch()