Update app.py

app.py

@@ -6,7 +6,11 @@ from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
 import torch
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "Lykon/dreamshaper-8" #Replace to the model you would like to use
+all_model_id = {
+    "DreamShaper-8": "Lykon/dreamshaper-8",
+    "SD-v1.4": "CompVis/stable-diffusion-v1-4",
+    "RealisticVision-v4.0": "SG161222/Realistic_Vision_V4.0_noVAE"
+}
 
 if torch.cuda.is_available():
     torch_dtype = torch.float16
@@ -17,7 +21,7 @@ MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
 #@spaces.GPU #[uncomment to use ZeroGPU]
-def infer_t2i(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
+def infer_t2i(model_repo_id, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
 
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
@@ -40,7 +44,7 @@ def infer_t2i(prompt, negative_prompt, seed, randomize_seed, width, height, guid
     return image, seed
 
 #@spaces.GPU #[uncomment to use ZeroGPU]
-def infer_i2i(prompt, image, strength, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
+def infer_i2i(model_repo_id, prompt, image, strength, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
 
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
@@ -64,6 +68,34 @@ def infer_i2i(prompt, image, strength, negative_prompt, seed, randomize_seed, wi
     
     return image, seed
 
+#@spaces.GPU #[uncomment to use ZeroGPU]
+def infer_ip_adapter(model_repo_id, prompt, image, scale, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
+
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+        
+    generator = torch.Generator().manual_seed(seed)
+
+    pipe = StableDiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
+    pipe = pipe.to(device)
+    pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter-plus_sd15.bin")
+    pipeline.set_ip_adapter_scale(scale)
+    
+    image = pipe(
+        prompt = prompt, 
+        image = image.resize((width, height)),
+        strength = strength,
+        negative_prompt = negative_prompt,
+        guidance_scale = guidance_scale, 
+        num_inference_steps = num_inference_steps, 
+        ip_adapter_image = image,
+        width = width, 
+        height = height,
+        generator = generator
+    ).images[0] 
+    
+    return image, seed
+
 examples = [
     "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
     "An astronaut riding a green horse",
@@ -116,6 +148,8 @@ with gr.Blocks(css=css) as demo:
                     step=1,
                     value=0,
                 )
+
+                model_choice = gr.Dropdown(label="Choose Model", choices=list(all_model_id.key()), value=list(all_model_id.key())[0])
                 
                 randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
                 
@@ -126,7 +160,7 @@ with gr.Blocks(css=css) as demo:
                         minimum=256,
                         maximum=MAX_IMAGE_SIZE,
                         step=32,
-                        value=1024, #Replace with defaults that work for your model
+                        value=512, #Replace with defaults that work for your model
                     )
                     
                     height = gr.Slider(
@@ -134,7 +168,7 @@ with gr.Blocks(css=css) as demo:
                         minimum=256,
                         maximum=MAX_IMAGE_SIZE,
                         step=32,
-                        value=1024, #Replace with defaults that work for your model
+                        value=512, #Replace with defaults that work for your model
                     )
                 
                 with gr.Row():
@@ -162,7 +196,7 @@ with gr.Blocks(css=css) as demo:
     
             run_button.click(
                 fn=infer_t2i,
-                inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+                inputs = [all_model_id[model_choice], prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
                 outputs = [result, seed]
             )
 
@@ -207,6 +241,8 @@ with gr.Blocks(css=css) as demo:
                 )
                 
                 randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+
+                model_choice = gr.Dropdown(label="Choose Model", choices=list(all_model_id.key()), value=list(all_model_id.key())[0])
                 
                 with gr.Row():
                     
@@ -215,7 +251,7 @@ with gr.Blocks(css=css) as demo:
                         minimum=256,
                         maximum=MAX_IMAGE_SIZE,
                         step=32,
-                        value=1024, #Replace with defaults that work for your model
+                        value=512, #Replace with defaults that work for your model
                     )
                     
                     height = gr.Slider(
@@ -223,7 +259,7 @@ with gr.Blocks(css=css) as demo:
                         minimum=256,
                         maximum=MAX_IMAGE_SIZE,
                         step=32,
-                        value=1024, #Replace with defaults that work for your model
+                        value=512, #Replace with defaults that work for your model
                     )
                 
                 with gr.Row():
@@ -259,7 +295,106 @@ with gr.Blocks(css=css) as demo:
     
             run_button.click(
                 fn=infer_i2i,
-                inputs = [prompt, image_upload_input, editing_strength, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+                inputs = [all_model_id[model_choice], prompt, image_upload_input, editing_strength, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+                outputs = [result, seed]
+            )
+
+    with gr.Tab("IP-Adapter"):
+
+        with gr.Column(elem_id="col-container"):
+            gr.Markdown(f"""
+            # Text-to-Image Gradio Template
+            """)
+            
+            with gr.Row():
+                
+                prompt = gr.Text(
+                    label="Prompt",
+                    show_label=False,
+                    max_lines=1,
+                    placeholder="Enter your prompt",
+                    container=False,
+                )
+                
+                run_button = gr.Button("Run", scale=0)
+
+            image_upload_input = gr.Image(label="Upload an Image", type="pil")
+            
+            result = gr.Image(label="Result", show_label=False)
+    
+            with gr.Accordion("Advanced Settings", open=False):
+                
+                negative_prompt = gr.Text(
+                    label="Negative prompt",
+                    max_lines=1,
+                    placeholder="Enter a negative prompt",
+                    visible=False,
+                )
+                
+                seed = gr.Slider(
+                    label="Seed",
+                    minimum=0,
+                    maximum=MAX_SEED,
+                    step=1,
+                    value=0,
+                )
+                
+                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+
+                model_choice = gr.Dropdown(label="Choose Model", choices=list(all_model_id.key()), value=list(all_model_id.key())[0])
+                
+                with gr.Row():
+                    
+                    width = gr.Slider(
+                        label="Width",
+                        minimum=256,
+                        maximum=MAX_IMAGE_SIZE,
+                        step=32,
+                        value=512, #Replace with defaults that work for your model
+                    )
+                    
+                    height = gr.Slider(
+                        label="Height",
+                        minimum=256,
+                        maximum=MAX_IMAGE_SIZE,
+                        step=32,
+                        value=512, #Replace with defaults that work for your model
+                    )
+                
+                with gr.Row():
+                    
+                    guidance_scale = gr.Slider(
+                        label="Guidance scale",
+                        minimum=0.0,
+                        maximum=10.0,
+                        step=0.1,
+                        value=7.5, #Replace with defaults that work for your model
+                    )
+                    
+                    num_inference_steps = gr.Slider(
+                        label="Number of inference steps",
+                        minimum=1,
+                        maximum=50,
+                        step=1,
+                        value=25, #Replace with defaults that work for your model
+                    )
+
+                    ip_adapter_scale = gr.Slider(
+                        label="Strength of image condition",
+                        minimum=0,
+                        maximum=1,
+                        step=0.01,
+                        value=0.4, #Replace with defaults that work for your model
+                    )
+            
+            gr.Examples(
+                examples = examples,
+                inputs = [prompt]
+            )
+    
+            run_button.click(
+                fn=infer_ip_adapter,
+                inputs = [all_model_id[model_choice], prompt, image_upload_input, ip_adapter_scale, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
                 outputs = [result, seed]
             )