Create app.py

app.py

@@ -0,0 +1,56 @@
+from PIL import Image
+import gradio as gr
+import numpy as np
+import torch
+from accelerate import Accelerator
+from transformers import pipeline
+from diffusers.utils import load_image
+from diffusers import KandinskyV22PriorPipeline, KandinskyV22ControlnetPipeline
+
+accelerator = Accelerator()
+
+def make_hint(image, depth_estimator):
+    image = depth_estimator(image)["depth"]
+    image = np.array(image)
+    image = image[:, :, None]
+    image = np.concatenate([image, image, image], axis=2)
+    detected_map = torch.from_numpy(image).float() / 255.0
+    hint = detected_map.permute(2, 0, 1)
+    return hint
+
+def plex(prompt,goof):
+    goof = load_image(goof).resize((768, 768))
+    depth_estimator = accelerator.prepare(pipeline("depth-estimation"))
+    hint = make_hint(goof, depth_estimator).unsqueeze(0).to("cpu")
+
+    pipe_prior = accelerator.prepare(KandinskyV22PriorPipeline.from_pretrained(
+        "kandinsky-community/kandinsky-2-2-prior", torch_dtype=torch.float32
+    ))
+    pipe_prior = accelerator.prepare(pipe_prior.to("cpu"))
+
+    pipe = accelerator.prepare(KandinskyV22ControlnetPipeline.from_pretrained(
+        "kandinsky-community/kandinsky-2-2-controlnet-depth", torch_dtype=torch.float32
+    ))
+    pipe = accelerator.prepare(pipe.to("cpu"))
+
+    negative_prior_prompt = "lowres,text,bad quality,jpeg artifacts,ugly,bad face,extra fingers,blurry,bad anatomy,bad proportions,extra limbs,fused fingers,long neck,watermark,signature"
+
+    generator = torch.Generator(device="cpu").manual_seed(random.randint(-1, 2147483647))
+    image_emb, zero_image_emb = pipe_prior(
+        prompt=prompt, negative_prompt=negative_prior_prompt, generator=generator
+    ).to_tuple()
+
+    images = pipe(
+        image_embeds=image_emb,
+        negative_image_embeds=zero_image_emb,
+        hint=hint,
+        num_inference_steps=50,
+        generator=generator,
+        height=768,
+        width=768,
+    ).images[0]
+
+    return images
+
+iface = gr.Interface(fn=plex,inputs=[gr.Textbox(),gr.Image(type="filepath")], outputs=gr.Image(), title="Img2Img_SkyV22CntrlNet", description="Running on CPU, very slow!")
+iface.launch()