Create app.py

app.py

@@ -0,0 +1,255 @@
+from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, EulerAncestralDiscreteScheduler
+from transformers import CLIPFeatureExtractor
+import gradio as gr
+import torch
+from PIL import Image
+import random
+import os
+from huggingface_hub import hf_hub_download
+
+
+model_id = 'aipicasso/picasso-diffusion-1-1'
+auth_token=os.environ.get("ACCESS_TOKEN")
+
+scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler", use_auth_token=auth_token)
+feature_extractor = CLIPFeatureExtractor.from_pretrained(model_id, use_auth_token=auth_token)
+
+pipe_merged = StableDiffusionPipeline.from_pretrained(
+  model_id,
+  torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+  scheduler=scheduler, use_auth_token=auth_token)
+
+pipe_i2i_merged = StableDiffusionImg2ImgPipeline.from_pretrained(
+  model_id,
+  torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+  scheduler=scheduler,
+  requires_safety_checker=False,
+  safety_checker=None,
+  feature_extractor=feature_extractor, use_auth_token=auth_token
+)
+
+pipe=pipe_merged.to("cuda")
+pipe_i2i=pipe_i2i_merged.to("cuda")
+pipe.enable_xformers_memory_efficient_attention()
+pipe_i2i.enable_xformers_memory_efficient_attention()
+
+embeddings_path=hf_hub_download(repo_id=model_id, filename="embeddings/negative/nfixer.pt", use_auth_token=auth_token)
+embeddings_dict=torch.load(embeddings_path)
+print(embeddings_dict)
+if "string_to_param" in embeddings_dict:
+    embeddings = next(iter(embeddings_dict['string_to_param'].values()))
+    nfixer = ""
+    for i, emb in enumerate(embeddings):
+        token = f"sksd{chr(i+65)}"
+        nfixer += token
+        pipe.tokenizer.add_tokens(token)
+        pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer))
+        token_id = pipe.tokenizer.convert_tokens_to_ids(token)
+        pipe.text_encoder.get_input_embeddings().weight.data[token_id] = emb
+else:
+    nfixer = list(embeddings_dict.keys())[0]
+    embeddings = embeddings_dict[nfixer].to(pipe.text_encoder.get_input_embeddings().weight.dtype)
+    pipe.tokenizer.add_tokens(placeholder_token)
+    pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer))
+    placeholder_token_id = pipe.tokenizer.convert_tokens_to_ids(placeholder_token)
+    pipe.text_encoder.get_input_embeddings().weight.data[placeholder_token_id] = embeddings
+
+embeddings_path=hf_hub_download(repo_id=model_id, filename="embeddings/positive/embellish1.pt", use_auth_token=auth_token)
+embeddings_dict=torch.load(embeddings_path)
+print(embeddings_dict)
+if "string_to_param" in embeddings_dict:
+    embeddings = next(iter(embeddings_dict['string_to_param'].values()))
+    embellish1 = ""
+    for i, emb in enumerate(embeddings):
+        token = f"kskd{chr(i%26+65)}{chr(i//26+65)}"
+        embellish1 += token
+        pipe.tokenizer.add_tokens(token)
+        pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer))
+        token_id = pipe.tokenizer.convert_tokens_to_ids(token)
+        pipe.text_encoder.get_input_embeddings().weight.data[token_id] = emb
+else:
+    embellish1 = list(embeddings_dict.keys())[0]
+    embeddings = embeddings_dict[embellish2].to(pipe.text_encoder.get_input_embeddings().weight.dtype)
+    pipe.tokenizer.add_tokens(placeholder_token)
+    pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer))
+    placeholder_token_id = pipe.tokenizer.convert_tokens_to_ids(placeholder_token)
+    pipe.text_encoder.get_input_embeddings().weight.data[placeholder_token_id] = embeddings
+
+def error_str(error, title="Error"):
+    return f"""#### {title}
+            {error}"""  if error else ""
+
+def inference(prompt, guidance, steps, image_size="Square", seed=0, img=None, strength=0.5, neg_prompt="", disable_auto_prompt_correction=False, image_style="Animetic", original_model=False):
+  global pipe,pipe_i2i
+  
+  generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
+
+  prompt,neg_prompt=auto_prompt_correction(prompt,neg_prompt,disable_auto_prompt_correction,image_style)
+
+  if(image_size=="Portrait"):
+      height=1024
+      width=768
+  elif(image_size=="Landscape"):
+      height=768
+      width=1024  
+  elif(image_size=="Highreso."):
+      height=1024
+      width=1024  
+  else:
+      height=768
+      width=768
+
+  print(prompt,neg_prompt)
+    
+  try:
+    if img is not None:
+      return img_to_img(prompt, neg_prompt, img, strength, guidance, steps, width, height, generator), None
+    else:
+      return txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator), None
+  except Exception as e:
+    return None, error_str(e)
+def auto_prompt_correction(prompt_ui,neg_prompt_ui,disable_auto_prompt_correction,image_style):
+    # auto prompt correction
+    prompt=str(prompt_ui)
+    neg_prompt=str(neg_prompt_ui)
+    prompt=prompt.lower()
+    neg_prompt=neg_prompt.lower()
+
+    if(image_style=="Animetic"):
+        style="anime"
+    else:
+        style=f"anime,{embellish1}"
+    
+    if(disable_auto_prompt_correction):
+        prompt=f"{style}, {prompt}"
+        return prompt, neg_prompt
+
+    if(prompt=="" and neg_prompt==""):
+        prompt=f"{style}, masterpiece, portrait, a girl with flowers, good pupil, detailed"
+        neg_prompt=f"{nfixer},(((deformed))), blurry, ((((bad anatomy)))),3d, cg, text , bad pupil, disfigured, poorly drawn face, mutation, mutated, (extra limb), (ugly), (poorly drawn hands), bad hands, fused fingers, messy drawing, broken legs censor, low quality, (mutated hands and fingers:1.5), (long body :1.3), (mutation, poorly drawn :1.2), ((bad eyes)), ui, error, missing fingers, fused fingers, one hand with more than 5 fingers, one hand with less than 5 fingers, one hand with more than 5 digit, one hand with less than 5 digit, extra digit, fewer digits, fused digit, missing digit, bad digit, liquid digit, long body, uncoordinated body, unnatural body, lowres, jpeg artifacts"
+        return prompt, neg_prompt
+
+    splited_prompt=prompt.replace(","," ").replace("_"," ").split(" ")
+    
+    human_words=["1girl","girl","maid","maids","female","1woman","woman","girls","2girls","3girls","4girls","5girls","a couple of girls","women","1boy","boy","boys","a couple of boys","2boys","male","1man","1handsome","1bishounen","man","men","guy","guys"]
+    for word in human_words:
+        if( word in splited_prompt):
+            prompt=f"{style}, masterpiece, {prompt}, good pupil, detailed"
+            neg_prompt=f"{nfixer},(((deformed))), blurry, ((((bad anatomy)))), {neg_prompt}, 3d, cg, text, bad pupil, disfigured, poorly drawn face, mutation, mutated, (extra limb), (ugly), (poorly drawn hands), bad hands, fused fingers, messy drawing, broken legs censor, low quality, (mutated hands and fingers:1.5), (long body :1.3), (mutation, poorly drawn :1.2), ((bad eyes)), ui, error, missing fingers, fused fingers, one hand with more than 5 fingers, one hand with less than 5 fingers, one hand with more than 5 digit, one hand with less than 5 digit, extra digit, fewer digits, fused digit, missing digit, bad digit, liquid digit, long body, uncoordinated body, unnatural body, lowres, jpeg artifacts"
+            return prompt, neg_prompt
+            
+    animal_words=["cat","dog","bird","pigeon","rabbit","bunny","horse"]
+    for word in animal_words:
+        if( word in splited_prompt):
+            prompt=f"{style}, a {prompt}, 4k, detailed"
+            neg_prompt=f"{nfixer}, girl, (((deformed))), blurry, ((((bad anatomy)))), {neg_prompt}, 3d, cg, text, bad pupil, disfigured, poorly drawn face, mutation, mutated, (extra limb), (ugly), (poorly drawn hands), bad hands, fused fingers, messy drawing, broken legs censor, low quality, (mutated hands and fingers:1.5), (long body :1.3), (mutation, poorly drawn :1.2), ((bad eyes)), ui, error, missing fingers, fused fingers, one hand with more than 5 fingers, one hand with less than 5 fingers, one hand with more than 5 digit, one hand with less than 5 digit, extra digit, fewer digits, fused digit, missing digit, bad digit, liquid digit, long body, uncoordinated body, unnatural body, lowres, jpeg artifacts"
+            return prompt, neg_prompt
+            
+    background_words=["mount fuji","mt. fuji","building", "buildings", "tokyo", "kyoto", "nara", "shibuya", "shinjuku"]
+    for word in background_words:
+        if( word in splited_prompt):
+            prompt=f"{style}, shinkai makoto, {word}, highly detailed"
+            neg_prompt=f"girl, (((deformed))), {neg_prompt}, girl, boy, photo, people, low quality, ui, error, lowres, jpeg artifacts, 2d, 3d, cg, text"
+            return prompt, neg_prompt
+            
+    return prompt,neg_prompt
+    
+def txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator):
+    result = pipe(
+      prompt,
+      negative_prompt = neg_prompt,
+      num_inference_steps = int(steps),
+      guidance_scale = guidance,
+      width = width,
+      height = height,
+      generator = generator)
+    
+    return result.images[0]
+
+def img_to_img(prompt, neg_prompt, img, strength, guidance, steps, width, height, generator):
+    ratio = min(height / img.height, width / img.width)
+    img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
+    result = pipe_i2i(
+        prompt,
+        negative_prompt = neg_prompt,
+        image = img,
+        num_inference_steps = int(steps),
+        strength = strength,
+        guidance_scale = guidance,
+        generator = generator)
+        
+    return result.images[0]
+
+css = """.main-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.main-div div h1{font-weight:900;margin-bottom:7px}.main-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem}
+"""
+with gr.Blocks(css=css) as demo:
+    gr.HTML(
+        f"""
+            <div class="main-div">
+              <div>
+                <h1>Picasso Diffusion 1.1 Demo</h1>
+              </div>
+              <p>
+               Demo for <a href="https://huggingface.co/alfredplpl/picasso-diffusion-1-1">Picasso Diffusion 1.1</a><br>
+              </p>
+              <p>
+              サンプル： そのままGenerateボタンを押してください。<br>
+              sample : Click "Generate" button without any prompts.
+              </p>
+              <p>
+              sample prompt1 : girl, kimono
+              </p>
+              <p>
+              sample prompt2 : boy, armor
+              </p>
+              Running on {"<b>GPU 🔥</b>" if torch.cuda.is_available() else f"<b>CPU 🥶</b>. For faster inference it is recommended to <b>upgrade to GPU in <a href='https://huggingface.co/spaces/akhaliq/cool-japan-diffusion-2-1-0/settings'>Settings</a></b>"} <br>
+              <a style="display:inline-block" href="https://huggingface.co/spaces/aipicasso/picasso-diffusion-latest-demo?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a> to say goodbye from waiting for the generating.
+            </div>
+        """
+    )
+    with gr.Row():
+        
+        with gr.Column(scale=55):
+          with gr.Group():
+              with gr.Row():
+                image_style=gr.Radio(["Realistic","Animetic"])
+                image_style.show_label=False
+                image_style.value="Animetic"
+            
+              with gr.Row():
+                prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="[your prompt]").style(container=False)
+                generate = gr.Button(value="Generate").style(rounded=(False, True, True, False))
+
+              image_out = gr.Image(height=768,width=768)
+          error_output = gr.Markdown()
+
+        with gr.Column(scale=45):
+          with gr.Tab("Options"):
+            with gr.Group():
+              neg_prompt = gr.Textbox(label="Negative prompt", placeholder="What to exclude from the image")
+              disable_auto_prompt_correction = gr.Checkbox(label="Disable auto prompt corretion.")
+              #original_model = gr.Checkbox(label="Change the model into the original model.")
+              with gr.Row():
+                image_size=gr.Radio(["Portrait","Landscape","Square","Highreso."])
+                image_size.show_label=False
+                image_size.value="Square"
+                
+              with gr.Row():
+                guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=15)
+                steps = gr.Slider(label="Steps", value=20, minimum=2, maximum=75, step=1)
+
+              seed = gr.Slider(0, 2147483647, label='Seed (0 = random)', value=0, step=1)
+
+          with gr.Tab("Image to image"):
+              with gr.Group():
+                image = gr.Image(label="Image", height=256, tool="editor", type="pil")
+                strength = gr.Slider(label="Transformation strength", minimum=0, maximum=1, step=0.01, value=0.5)
+                  
+    inputs = [prompt, guidance, steps, image_size, seed, image, strength, neg_prompt, disable_auto_prompt_correction,image_style]#, original_model]
+
+    outputs = [image_out, error_output]
+    prompt.submit(inference, inputs=inputs, outputs=outputs)
+    generate.click(inference, inputs=inputs, outputs=outputs)#,api_name="generate"
+
+demo.queue(concurrency_count=1)
+demo.launch()