Emi

.gitattributes

@@ -32,3 +32,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+manual.safetensors filter=lfs diff=lfs merge=lfs -text
+unaestheticXLv1.safetensors filter=lfs diff=lfs merge=lfs -text
+unaestheticXLv13.safetensors filter=lfs diff=lfs merge=lfs -text
+unaestheticXLv31.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,10 +1,10 @@
 ---
-title: Picasso Diffusion
-emoji: 🎨
-colorFrom: purple
-colorTo: gray
+title: Emi
+emoji: 😊
+colorFrom: blue
+colorTo: blue
 sdk: gradio
-sdk_version: 3.17.0
+sdk_version: 3.41.2
 app_file: app.py
 pinned: false
 license: other

app.py

@@ -1,183 +1,160 @@
-from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, EulerAncestralDiscreteScheduler
-from transformers import CLIPFeatureExtractor
+from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline, EulerAncestralDiscreteScheduler
 import gradio as gr
 import torch
 from PIL import Image
 import random
 import os
 from huggingface_hub import hf_hub_download
+import torch
+from torch import autocast
+from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
+from safetensors import safe_open
+from compel import Compel, ReturnedEmbeddingsType
+from huggingface_hub import hf_hub_download
 
-
-model_id = 'aipicasso/picasso-diffusion-1-1'
-auth_token=os.environ.get("ACCESS_TOKEN")
+model_id = 'aipicasso/emi'
+auth_token=os.environ["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(
+pipe = StableDiffusionXLPipeline.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
+
+pipe=pipe.to("cuda")
+#pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+token_num=65
+
+unaestheticXLv31=""
+embeddings_dict = {}
+with safe_open("unaestheticXLv31.safetensors", framework="pt") as f:
+    for k in f.keys():
+        embeddings_dict[k] = f.get_tensor(k)
+pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128)
+pipe.text_encoder_2.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128)
+for i in range(len(embeddings_dict["clip_l"])):
+    token = f"sksd{chr(token_num)}"
+    token_num+=1
+    unaestheticXLv31 += token
+    pipe.tokenizer.add_tokens(token)
+    token_id = pipe.tokenizer.convert_tokens_to_ids(token)
+    pipe.text_encoder.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_l"][i]
+    pipe.text_encoder_2.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_g"][i]
+
+unaestheticXLv1=""
+embeddings_dict = {}
+with safe_open("unaestheticXLv1.safetensors", framework="pt") as f:
+    for k in f.keys():
+        embeddings_dict[k] = f.get_tensor(k)
+pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128)
+pipe.text_encoder_2.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128)
+for i in range(len(embeddings_dict["clip_l"])):
+    token = f"sksd{chr(token_num)}"
+    token_num+=1
+    unaestheticXLv1 += token
+    pipe.tokenizer.add_tokens(token)
+    token_id = pipe.tokenizer.convert_tokens_to_ids(token)
+    pipe.text_encoder.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_l"][i]
+    pipe.text_encoder_2.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_g"][i]
+
+unaestheticXLv13=""
+embeddings_dict = {}
+with safe_open("unaestheticXLv13.safetensors", framework="pt") as f:
+    for k in f.keys():
+        embeddings_dict[k] = f.get_tensor(k)
+
+pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128)
+pipe.text_encoder_2.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128)
+for i in range(len(embeddings_dict["clip_l"])):
+    token = f"sksd{chr(token_num)}"
+    unaestheticXLv13 += token
+    token_num+=1
+    pipe.tokenizer.add_tokens(token)
+    token_id = pipe.tokenizer.convert_tokens_to_ids(token)
+    pipe.text_encoder.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_l"][i]
+    pipe.text_encoder_2.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_g"][i]
+
+
+compel = Compel(tokenizer=[pipe.tokenizer, pipe.tokenizer_2] , 
+                text_encoder=[pipe.text_encoder, pipe.text_encoder_2], 
+                returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED, 
+                requires_pooled=[False, True])
 
 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
-  
+def inference(prompt, guidance, steps, seed=0, neg_prompt="", disable_auto_prompt_correction=False):
+  global pipe
+    
   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
+  prompt,neg_prompt=auto_prompt_correction(prompt,neg_prompt,disable_auto_prompt_correction)
+
+  height=1024
+  width=1024
 
   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):
+  return txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator), None
+
+def auto_prompt_correction(prompt_ui,neg_prompt_ui,disable_auto_prompt_correction):
     # 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"
+        prompt="1girl++, smile--, brown bob+++ hair, brown eyes, sunflowers, sky, transparent++"
+        neg_prompt=f"({unaestheticXLv31})---, photo, deformed, realism, disfigured, low contrast, bad hand"
         return prompt, neg_prompt
 
-    splited_prompt=prompt.replace(","," ").replace("_"," ").split(" ")
+    splited_prompt=prompt.replace(","," ").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"
+            prompt=f"anime artwork, anime style, {prompt}"
+            neg_prompt=f"({unaestheticXLv31})---,{neg_prompt}, photo, deformed, realism, disfigured, low contrast, bad hand" 
             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"
+            prompt=f"anime style, a {prompt}, 4k, detailed"
+            neg_prompt=f"{neg_prompt},({unaestheticXLv31})---" 
             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"
+            prompt=f"anime artwork, anime style, {prompt}, 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)
+    conditioning, pooled = compel([prompt, neg_prompt])
     
-    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,
+    result = pipe(
+        prompt_embeds=conditioning[0:1],
+        pooled_prompt_embeds=pooled[0:1], 
+        negative_prompt_embeds=conditioning[1:2], 
+        negative_pooled_prompt_embeds=pooled[1:2],
         num_inference_steps = int(steps),
-        strength = strength,
         guidance_scale = guidance,
+        width = width,
+        height = height,
         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}
@@ -187,23 +164,36 @@ with gr.Blocks(css=css) as demo:
         f"""
             <div class="main-div">
               <div>
-                <h1>Picasso Diffusion 1.1 Demo</h1>
+                <h1>Emi Demo</h1>
               </div>
               <p>
-               Demo for <a href="https://huggingface.co/alfredplpl/picasso-diffusion-1-1">Picasso Diffusion 1.1</a><br>
+               Demo for <a href="https://huggingface.co/aipicasso/emi">Emi</a><br>
               </p>
               <p>
               サンプル： そのままGenerate��タンを押してください。<br>
               sample : Click "Generate" button without any prompts.
               </p>
               <p>
-              sample prompt1 : girl, kimono
+              sample prompt1 : 1girl++, cool+, smile--, colorful long hair, colorful eyes, stars, night, pastel color, transparent+
+              </p>
+              <p>
+              sample prompt2 : 1man+, focus, wavy short hair, blue eyes, black shirt, white background, simple background
               </p>
               <p>
-              sample prompt2 : boy, armor
+              sample prompt3 : anime style, 1girl++
               </p>
+              <p>
+              共有ボタンを押してみんなに画像を共有しましょう。Please push share button to share your image.
+              </p>
+              <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.
+              <a style="display:inline-block" href="https://huggingface.co/spaces/aipicasso/emi-latest-demo?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a> to say goodbye from waiting for the generating.
+              <h2>
+                <a href="https://e5b26b1151bf4a7fe2.gradio.live"> | Emi Demo (Sub) | </a> 
+                <a href="https://e4f3a9ae48c8c4921e.gradio.live"> Emi Stable Demo | </a> 
+                <a href="https://07f0307923ad05d680.gradio.live"> Emix Demo 1 |</a> 
+                <a href="https://471d8ebdaf5d5c5aa5.gradio.live/"> Emix Demo 2 |</a> 
+              </h2>
             </div>
         """
     )
@@ -212,44 +202,28 @@ with gr.Blocks(css=css) as demo:
         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))
+                prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="[your prompt]")
+                generate = gr.Button(value="Generate")
 
-              image_out = gr.Image(height=768,width=768)
+              image_out = gr.Image(height=1024,width=1024)
           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)
+                guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=25)
                 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]
+    inputs = [prompt, guidance, steps, seed, neg_prompt, disable_auto_prompt_correction]
 
     outputs = [image_out, error_output]
     prompt.submit(inference, inputs=inputs, outputs=outputs)
-    generate.click(inference, inputs=inputs, outputs=outputs)#,api_name="generate"
-
+    generate.click(inference, inputs=inputs, outputs=outputs)
+    
 demo.queue(concurrency_count=1)
-demo.launch()
+demo.launch()

requirements.txt

@@ -1,8 +1,10 @@
---extra-index-url https://download.pytorch.org/whl/cu117
 torch
+xformers
 diffusers
 transformers
 accelerate
 ftfy
 triton
-xformers
+safetensors
+compel
+omegaconf