Duplicate from Thafx/sdrv51

Co-authored-by: ThaFX <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,20 @@
+---
+title: Realistic Vision v5.1
+emoji: 📷
+colorFrom: yellow
+colorTo: red
+sdk: gradio
+sdk_version: 3.18.0
+app_file: app.py
+pinned: true
+duplicated_from: Thafx/sdrv51
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- realistic-vision
+models:
+- SG161222/Realistic_Vision_V5.1_noVAE
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,189 @@
+from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler
+import gradio as gr
+import torch
+from PIL import Image
+
+model_id = 'SG161222/Realistic_Vision_V5.1_noVAE'
+prefix = 'RAW photo,'
+     
+scheduler = DPMSolverMultistepScheduler.from_pretrained(model_id, subfolder="scheduler")
+
+pipe = StableDiffusionPipeline.from_pretrained(
+  model_id,
+  torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+  scheduler=scheduler)
+
+pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(
+  model_id,
+  torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+  scheduler=scheduler)
+
+if torch.cuda.is_available():
+  pipe = pipe.to("cuda")
+  pipe_i2i = pipe_i2i.to("cuda")
+
+def error_str(error, title="Error"):
+    return f"""#### {title}
+            {error}"""  if error else ""
+
+
+def _parse_args(prompt, generator):
+        parser = argparse.ArgumentParser(
+            description="making it work."
+        )
+        parser.add_argument(
+            "--no-half-vae", help="no half vae"
+        )
+
+        cmdline_args = parser.parse_args()
+        command = cmdline_args.command
+        conf_file = cmdline_args.conf_file
+        conf_args = Arguments(conf_file)
+        opt = conf_args.readArguments()
+
+        if cmdline_args.config_overrides:
+            for config_override in cmdline_args.config_overrides.split(";"):
+                config_override = config_override.strip()
+                if config_override:
+                    var_val = config_override.split("=")
+                    assert (
+                        len(var_val) == 2
+                    ), f"Config override '{var_val}' does not have the form 'VAR=val'"
+                    conf_args.add_opt(opt, var_val[0], var_val[1], force_override=True)
+
+def inference(prompt, guidance, steps, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt="", auto_prefix=False):
+  generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
+  prompt = f"{prefix} {prompt}" if auto_prefix else 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 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,
+        init_image = img,
+        num_inference_steps = int(steps),
+        strength = strength,
+        guidance_scale = guidance,
+        width = width,
+        height = height,
+        generator = generator)
+        
+    return result.images[0]
+
+    def fake_safety_checker(images, **kwargs):
+      return result.images[0], [False] * len(images)
+    
+    pipe.safety_checker = fake_safety_checker
+
+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 style="color:orange;">📷 Realistic Vision V5.1 📸</h1>
+              </div>
+              <p>
+               Demo for <a href="https://huggingface.co/SG161222/Realistic_Vision_V5.1_noVAE">Realistic Vision V5.1</a>
+               Stable Diffusion model by <a href="https://huggingface.co/SG161222/"><abbr title="SG1611222">Eugene</abbr></a>.  {"" if prefix else ""}  
+              Running on {"<b>GPU 🔥</b>" if torch.cuda.is_available() else f"<b>CPU ⚡</b>"}. 
+              </p>
+           <p>Please use the prompt template below to get an example of the desired generation results:
+           </p>
+
+<b>Prompt</b>:
+<details><code>
+* subject *, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
+<br>
+<br>
+<q><i>
+Example: a close up portrait photo of 26 y.o woman in wastelander clothes, long haircut, pale skin, slim body, background is city ruins, <br>
+(high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 
+</i></q>
+</code></details>
+
+<br>
+<b>Negative Prompt</b>:
+<details><code>
+(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, <br>
+low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, <br>
+dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, <br>
+extra legs, fused fingers, too many fingers, long neck
+</code></details>
+
+<br>
+Have Fun & Enjoy ⚡ <a href="https://www.thafx.com"><abbr title="Website">//THAFX</abbr></a>
+<br>
+             
+            </div>
+        """
+    )
+    with gr.Row():
+        
+        with gr.Column(scale=55):
+          with gr.Group():
+              with gr.Row():
+                prompt = gr.Textbox(label="Prompt", show_label=False,max_lines=2,placeholder=f"{prefix} [your prompt]").style(container=False)
+                generate = gr.Button(value="Generate").style(rounded=(False, True, True, False))
+
+              image_out = gr.Image(height=512)
+          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")
+              auto_prefix = gr.Checkbox(label="Prefix styling tokens automatically (RAW photo,)", value=prefix, visible=prefix)
+
+              with gr.Row():
+                guidance = gr.Slider(label="Guidance scale", value=5, maximum=15)
+                steps = gr.Slider(label="Steps", value=20, minimum=2, maximum=75, step=1)
+
+              with gr.Row():
+                width = gr.Slider(label="Width", value=512, minimum=64, maximum=1024, step=8)
+                height = gr.Slider(label="Height", value=512, minimum=64, maximum=1024, step=8)
+
+              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)
+
+    auto_prefix.change(lambda x: gr.update(placeholder=f"{prefix} [your prompt]" if x else "[Your prompt]"), inputs=auto_prefix, outputs=prompt, queue=False)
+
+    inputs = [prompt, guidance, steps, width, height, seed, image, strength, neg_prompt, auto_prefix]
+    outputs = [image_out, error_output]
+    prompt.submit(inference, inputs=inputs, outputs=outputs)
+    generate.click(inference, inputs=inputs, outputs=outputs)
+
+    
+
+demo.queue(concurrency_count=1)
+demo.launch()

requirements.txt

@@ -0,0 +1,10 @@
+--extra-index-url https://download.pytorch.org/whl/cu113
+invisible-watermark
+fonts
+font-roboto
+torch
+diffusers
+transformers
+git+https://github.com/huggingface/transformers
+accelerate
+ftfy