Create app.py

app.py

@@ -0,0 +1,68 @@
+
+import torch
+from PIL import Image
+from diffusers import ControlNetModel, DiffusionPipeline
+from diffusers.utils import load_image
+import gradio as gr 
+import warnings
+warnings.filterwarnings("ignore")
+def resize_for_condition_image(input_image: Image, resolution: int):
+    input_image = input_image.convert("RGB")
+    W, H = input_image.size
+    k = float(resolution) / min(H, W)
+    H *= k
+    W *= k
+    H = int(round(H / 64.0)) * 64
+    W = int(round(W / 64.0)) * 64
+    img = input_image.resize((W, H), resample=Image.LANCZOS)
+    return img
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+controlnet = ControlNetModel.from_pretrained('lllyasviel/control_v11f1e_sd15_tile', 
+                                             torch_dtype=torch.float16)
+pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5",
+                                         custom_pipeline="stable_diffusion_controlnet_img2img",
+                                         controlnet=controlnet,
+                                         torch_dtype=torch.float16).to(device)
+pipe.enable_xformers_memory_efficient_attention()
+
+source_image = load_image('https://huggingface.co/lllyasviel/control_v11f1e_sd15_tile/resolve/main/images/original.png')
+
+
+def super_esr(source_image,prompt,negative_prompt,strength,seed,num_inference_steps):
+    condition_image = resize_for_condition_image(source_image, 1024)
+    image = pipe(prompt=prompt,#"best quality", 
+                negative_prompt="blur, lowres, bad anatomy, bad hands, cropped, worst quality", 
+                image=condition_image, 
+                controlnet_conditioning_image=condition_image, 
+                width=condition_image.size[0],
+                height=condition_image.size[1],
+                strength=1.0,
+                generator=seed,
+                num_inference_steps=num_inference_steps,
+                ).image
+    print(source_image,prompt,negative_prompt,strength,seed,num_inference_steps)
+    return source_image
+
+#define laund take input nsame as super_esr function
+def launch():
+    inputs=[
+        gr.inputs.Image(type="pil",label="Source Image"),
+        gr.inputs.Textbox(lines=2,label="Prompt"),
+        gr.inputs.Textbox(lines=2,label="Negative Prompt"),
+        gr.inputs.Slider(minimum=0,maximum=1,label="Strength"),
+        gr.inputs.Slider(minimum=0,maximum=100,label="Seed"),
+        gr.inputs.Slider(minimum=0,maximum=100,label="Num Inference Steps")
+    ]
+    outputs=[
+        gr.outputs.Image(type="pil",label="Output Image")
+    ]
+    title="Super ESR"
+    description="Super ESR is a super resolution model that uses diffusion to generate high resolution images from low resolution images"
+    examples=[
+        ["https://i.imgur.com/9IqyX1F.png","best quality","blur, lowres, bad anatomy, bad hands, cropped, worst quality",1.0,0,100],
+        ["https://i.imgur.com/9IqyX1F.png","best quality","blur, lowres, bad anatomy, bad hands, cropped, worst quality",1.0,0,100],
+    ]
+    gr.Interface(fn=super_esr,inputs=inputs,outputs=outputs,title=title,description=description,examples=examples).launch(share=True)
+
+launch()