final_app_py

app.py

@@ -1,52 +1,122 @@
 import gradio as gr
 import numpy as np
 import random
+from typing import Optional
 
 # import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
+from diffusers import StableDiffusionPipeline, StableDiffusionControlNetPipeline
+from diffusers import ControlNetModel
+from peft import PeftModel, LoraConfig
+from PIL import Image
+import cv2
+
 import torch
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
 
 if torch.cuda.is_available():
     torch_dtype = torch.float16
 else:
     torch_dtype = torch.float32
 
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
+import os
+# import torch
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
 
+CONTROL_MODE_MODEL = {
+"Canny Ege Detection" : "lllyasviel/control_v11p_sd15_canny",
+"Pixel to Pixel": "lllyasviel/control_v11e_sd15_ip2p",
+"M-LSD Line detection" : "lllyasviel/control_v11p_sd15_mlsd",
+"HED edge detection (soft edge)" : "lllyasviel/control_sd15_hed",
+"Midas depth estimationn" : "lllyasviel/control_v11f1p_sd15_depth",
+"Surface Normal Estimation" : "lllyasviel/control_v11p_sd15_normalbae",
+"Scribble-Based Generation" : "lllyasviel/control_v11p_sd15_scribble",
+"Semantic segmentation" : "lllyasviel/control_v11p_sd15_seg",
+"OpenPose pose detection" : "lllyasviel/control_v11p_sd15_openpose",
+"Line Art Generation": "lllyasviel/control_v11p_sd15_lineart",
+}
+
 # @spaces.GPU #[uncomment to use ZeroGPU]
 def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
+    prompt: str,
+    negative_prompt : str,
     width,
     height,
-    guidance_scale,
-    num_inference_steps,
+    lscale=0.0,
+    controlnet_enabled=False,
+    controlnet_strength=0.0,
+    controlnet_mode=None,
+    controlnet_image=None,
+    ip_adapter_enabled=False,
+    ip_adapter_scale=0.0,
+    ip_adapter_image=None,
+    model_id: Optional[str]  = "CompVis/stable-diffusion-v1-4",
+    seed: Optional[int] = 42,
+    guidance_scale : Optional[int] = 7,
+    num_inference_steps : Optional[int] = 20,
     progress=gr.Progress(track_tqdm=True),
 ):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
+    # if model_id != "CompVis/stable-diffusion-v1-4":
+    #    raise ValueError("The submitted model is not supported")
     generator = torch.Generator().manual_seed(seed)
 
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
+    if controlnet_enabled:
+        if not controlnet_image :
+            raise ValueError("controlnet_enabled set to True, but controlnet_image not given")
+        else:
+            controlnet_model = ControlNetModel.from_pretrained(CONTROL_MODE_MODEL.get(controlnet_mode))
+        if model_id == "SD-v1-5 + Lora" :
+            pipe=StableDiffusionControlNetPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5",controlnet=controlnet_model, torch_dtype=torch_dtype)
+            pipe.unet = PeftModel.from_pretrained("Emilichcka/diffusion_lora_funny_cat", "./unet", torch_dtype=torch_dtype)
+            pipe.text_encoder = PeftModel.from_pretrained("Emilichcka/diffusion_lora_funny_cat", "./text_encoder", torch_dtype=torch_dtype)
+
+        else:
+            pipe=StableDiffusionControlNetPipeline.from_pretrained(model_id, controlnet=controlnet_model, torch_dtype=torch_dtype)
+    else:
+        if model_id == "SD-v1-5 + Lora" :
+            pipe=StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5",torch_dtype=torch_dtype)
+            pipe.unet = PeftModel.from_pretrained("Emilichcka/diffusion_lora_funny_cat", "./unet", torch_dtype=torch_dtype)
+            pipe.text_encoder = PeftModel.from_pretrained("Emilichcka/diffusion_lora_funny_cat", "./text_encoder", torch_dtype=torch_dtype)
+        else:
+            pipe=StableDiffusionPipeline.from_pretrained(model_id)
+
+    if ip_adapter_enabled:
+            ip_adapter_scale = float(ip_adapter_scale)
+            pipe.load_ip_adapter("h94/IP-Adapter",subfolder="models", weight_name="ip-adapter-plus_sd15.bin")
+            pipe.set_ip_adapter_scale(ip_adapter_scale)
+
+    if controlnet_image!= None:
+      controlnet_image = np.array(controlnet_image)
+
+      low_threshold = 100
+      high_threshold = 200
+
+      controlnet_image = cv2.Canny(controlnet_image, low_threshold, high_threshold)
+      controlnet_image = controlnet_image[:, :, None]
+      controlnet_image = np.concatenate([controlnet_image, controlnet_image, controlnet_image], axis=2)
+      controlnet_image = Image.fromarray(controlnet_image)
+
+    pipe = pipe.to(device)
+
+    try:
+      image = pipe(
+          prompt=prompt,
+          image=controlnet_image,
+          negative_prompt=negative_prompt,
+          guidance_scale=guidance_scale,
+          num_inference_steps=num_inference_steps,
+          width=width,
+          height=height,
+          generator=generator,
+          ross_attention_kwargs={"scale": float(lscale)},
+          controlnet_conditioning_scale=controlnet_strength,
+          ip_adapter_image=ip_adapter_image,
+      ).images[0]
+    except Exception as e:
+            raise gr.Error(f"Ошибка при генерации изображения: {e}")
 
     return image, seed
 
@@ -60,14 +130,42 @@ examples = [
 css = """
 #col-container {
     margin: 0 auto;
-    max-width: 640px;
+    max-width: 880px;
 }
 """
 
+default_model_id_choice = [
+    "stable-diffusion-v1-5/stable-diffusion-v1-5",
+    "CompVis/stable-diffusion-v1-4",
+    "SD-v1-5 + Lora",
+
+]
+
+def update_controlnet_visibility(controlnet_enabled):
+    return gr.update(visible=controlnet_enabled), gr.update(visible=controlnet_enabled), gr.update(visible=controlnet_enabled)
+
+def update_ip_adapter_visibility(ip_adapter_enabled):
+    return gr.update(visible=ip_adapter_enabled), gr.update(visible=ip_adapter_enabled)
+
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
         gr.Markdown(" # Text-to-Image Gradio Template")
 
+        with gr.Row():
+            model_id = gr.Dropdown(
+            label="Model Selection",
+            choices=default_model_id_choice,
+            value="CompVis/stable-diffusion-v1-4",
+            )
+
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=42,
+            )
+
         with gr.Row():
             prompt = gr.Text(
                 label="Prompt",
@@ -81,24 +179,59 @@ with gr.Blocks(css=css) as demo:
 
         result = gr.Image(label="Result", show_label=False)
 
+        with gr.Row():
+            controlnet_enabled = gr.Checkbox(label="Enable ControlNet", value=False)
+            ip_adapter_enabled = gr.Checkbox(label="Enable IP-Adapter", value=False)
+
+        with gr.Accordion("ControlNet Settings", open=False):
+            gr.Markdown("Enable ControlNet to use settings", visible=True)
+            with gr.Row():
+                controlNet_strength = gr.Slider(
+                    label="ControlNet scale",
+                    minimum=0.0, maximum=1.0, step=0.05, value=0.75,
+                    visible=False,
+                    interactive=True,
+                )
+
+                controlNet_mode = gr.Dropdown(
+                    label="ControlNet Mode",
+                    choices=list(CONTROL_MODE_MODEL.keys()),
+                    visible=False,
+                    interactive=True,
+                )
+
+            controlNet_image = gr.Image(label="ControlNet Image", type="pil",
+                                        interactive=True, visible=False)
+
+        with gr.Accordion("IP-Adapter Settings", open=False):
+            gr.Markdown("Enable IP-Adapter to use settings", visible=True)
+            with gr.Row():
+                ip_adapter_scale = gr.Slider(
+                    label="IP-Adapter Scale",
+                    minimum=0.0, maximum=2.0, step=0.05, value=1.0,
+                    visible=False,
+                    interactive=True,
+                )
+
+            ip_adapter_image = gr.Image(label="IP-Adapter Image", type="pil",interactive=True, visible=False)
+
         with gr.Accordion("Advanced Settings", open=False):
             negative_prompt = gr.Text(
                 label="Negative prompt",
+                value="deformed, ugly,low res, worst quality, low quality",
                 max_lines=1,
                 placeholder="Enter a negative prompt",
-                visible=False,
             )
 
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
+            lora_scale = gr.Slider(
+                label="LoRA Scale",
+                minimum=0.0,
+                maximum=2.0,
+                step=0.1,
+                value=1.0,
+                info="Adjust the influence of the LoRA weights",
+                interactive=True,
             )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
             with gr.Row():
                 width = gr.Slider(
                     label="Width",
@@ -122,7 +255,7 @@ with gr.Blocks(css=css) as demo:
                     minimum=0.0,
                     maximum=10.0,
                     step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
+                    value=7.0,  # Replace with defaults that work for your model
                 )
 
                 num_inference_steps = gr.Slider(
@@ -130,25 +263,46 @@ with gr.Blocks(css=css) as demo:
                     minimum=1,
                     maximum=50,
                     step=1,
-                    value=2,  # Replace with defaults that work for your model
+                    value=20,  # Replace with defaults that work for your model
                 )
 
         gr.Examples(examples=examples, inputs=[prompt])
+
     gr.on(
         triggers=[run_button.click, prompt.submit],
         fn=infer,
         inputs=[
             prompt,
             negative_prompt,
-            seed,
-            randomize_seed,
             width,
             height,
+            lora_scale,
+            controlnet_enabled,
+            controlNet_strength,
+            controlNet_mode,
+            controlNet_image,
+            ip_adapter_enabled,
+            ip_adapter_scale,
+            ip_adapter_image,
+            model_id,
+            seed,
             guidance_scale,
             num_inference_steps,
         ],
         outputs=[result, seed],
     )
 
+    controlnet_enabled.change(
+        fn=update_controlnet_visibility,
+        inputs=[controlnet_enabled],
+        outputs=[controlNet_strength, controlNet_mode, controlNet_image],
+    )
+
+    ip_adapter_enabled.change(
+        fn=update_ip_adapter_visibility,
+        inputs=[ip_adapter_enabled],
+        outputs=[ip_adapter_scale, ip_adapter_image],
+    )
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)