First commit

app.py

@@ -0,0 +1,134 @@
+import gradio as gr
+
+import torch
+from torch import autocast
+from diffusers import StableDiffusionPipeline
+from datasets import load_dataset
+from PIL import Image
+import re
+from styles import css, header_html, footer_html
+from examples import examples
+from transformers import pipeline
+
+ars_model = pipeline("automatic-speech-recognition")
+
+
+model_id = "CompVis/stable-diffusion-v1-4"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# If you are running this code locally, you need to either do a 'huggingface-cli login` or paste your User Access Token from here https://huggingface.co/settings/tokens into the use_auth_token field below.
+pipe = StableDiffusionPipeline.from_pretrained(
+    model_id, use_auth_token=True, revision="fp16", torch_dtype=torch.float16)
+pipe = pipe.to(device)
+# When running locally, you won`t have access to this, so you can remove this part
+word_list_dataset = load_dataset(
+    "stabilityai/word-list", data_files="list.txt", use_auth_token=True)
+word_list = word_list_dataset["train"]['text']
+
+
+def transcribe(audio):
+    text = ars_model(audio)["text"]
+    return text
+
+
+def infer(audio, samples, steps, scale, seed):
+    prompt = transcribe(audio)
+    # When running locally you can also remove this filter
+    for filter in word_list:
+        if re.search(rf"\b{filter}\b", prompt):
+            raise gr.Error(
+                "Unsafe content found. Please try again with different prompts.")
+
+    generator = torch.Generator(device=device).manual_seed(seed)
+
+    # If you are running locally with CPU, you can remove the `with autocast("cuda")`
+    if device == "cuda":
+        with autocast("cuda"):
+            images_list = pipe(
+                [prompt] * samples,
+                num_inference_steps=steps,
+                guidance_scale=scale,
+                generator=generator,
+            )
+    else:
+        images_list = pipe(
+            [prompt] * samples,
+            num_inference_steps=steps,
+            guidance_scale=scale,
+            generator=generator,
+        )
+    images = []
+    safe_image = Image.open(r"unsafe.png")
+    for i, image in enumerate(images_list["sample"]):
+        if(images_list["nsfw_content_detected"][i]):
+            images.append(safe_image)
+        else:
+            images.append(image)
+    return images
+
+
+block = gr.Blocks(css=css)
+
+
+with block:
+    gr.HTML(header_html)
+    with gr.Group():
+        with gr.Box():
+            with gr.Row().style(mobile_collapse=False, equal_height=True):
+                audio = gr.Audio(
+                    label="Describe a prompt",
+                    source="microphone",
+                    type="filepath"
+                ).style(
+                    border=(True, False, True, True),
+                    rounded=(True, False, False, True),
+                    container=False,
+                )
+                btn = gr.Button("Generate image").style(
+                    margin=False,
+                    rounded=(False, True, True, False),
+                )
+
+        gallery = gr.Gallery(
+            label="Generated images", show_label=False, elem_id="gallery"
+        ).style(grid=[2], height="auto")
+
+        advanced_button = gr.Button("Advanced options", elem_id="advanced-btn")
+
+        with gr.Row(elem_id="advanced-options"):
+            samples = gr.Slider(label="Images", minimum=1,
+                                maximum=4, value=4, step=1)
+            steps = gr.Slider(label="Steps", minimum=1,
+                              maximum=50, value=45, step=1)
+            scale = gr.Slider(
+                label="Guidance Scale", minimum=0, maximum=50, value=7.5, step=0.1
+            )
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=2147483647,
+                step=1,
+                randomize=True,
+            )
+
+        ex = gr.Examples(fn=infer, inputs=[
+                         audio, samples, steps, scale, seed], outputs=gallery)
+        ex.dataset.headers = [""]
+
+        audio.submit(infer, inputs=[audio, samples,
+                                    steps, scale, seed], outputs=gallery)
+        btn.click(infer, inputs=[audio, samples, steps,
+                  scale, seed], outputs=gallery)
+        advanced_button.click(
+            None,
+            [],
+            audio,
+            _js="""
+            () => {
+                const options = document.querySelector("body > gradio-app").querySelector("#advanced-options");
+                options.style.display = ["none", ""].includes(options.style.display) ? "flex" : "none";
+            }""",
+        )
+        gr.HTML(footer_html)
+
+block.queue(max_size=25).launch()

examples.py

@@ -0,0 +1,37 @@
+examples = [
+    [
+        'A high tech solarpunk utopia in the Amazon rainforest',
+        4,
+        45,
+        7.5,
+        1024,
+    ],
+    [
+        'A pikachu fine dining with a view to the Eiffel Tower',
+        4,
+        45,
+        7,
+        1024,
+    ],
+    [
+        'A mecha robot in a favela in expressionist style',
+        4,
+        45,
+        7,
+        1024,
+    ],
+    [
+        'an insect robot preparing a delicious meal',
+        4,
+        45,
+        7,
+        1024,
+    ],
+    [
+        "A small cabin on top of a snowy mountain in the style of Disney, artstation",
+        4,
+        45,
+        7,
+        1024,
+    ],
+]

requirements.txt

@@ -0,0 +1,6 @@
+diffusers
+transformers
+datasets
+nvidia-ml-py3
+ftfy
+--extra-index-url https://download.pytorch.org/whl/cu113 torch

styles.py

@@ -0,0 +1,159 @@
+header_html = """
+            <div style="text-align: center; max-width: 650px; margin: 0 auto;">
+              <div
+                style="
+                  display: inline-flex;
+                  align-items: center;
+                  gap: 0.8rem;
+                  font-size: 1.75rem;
+                "
+              >
+                <svg
+                  width="0.65em"
+                  height="0.65em"
+                  viewBox="0 0 115 115"
+                  fill="none"
+                  xmlns="http://www.w3.org/2000/svg"
+                >
+                  <rect width="23" height="23" fill="white"></rect>
+                  <rect y="69" width="23" height="23" fill="white"></rect>
+                  <rect x="23" width="23" height="23" fill="#AEAEAE"></rect>
+                  <rect x="23" y="69" width="23" height="23" fill="#AEAEAE"></rect>
+                  <rect x="46" width="23" height="23" fill="white"></rect>
+                  <rect x="46" y="69" width="23" height="23" fill="white"></rect>
+                  <rect x="69" width="23" height="23" fill="black"></rect>
+                  <rect x="69" y="69" width="23" height="23" fill="black"></rect>
+                  <rect x="92" width="23" height="23" fill="#D9D9D9"></rect>
+                  <rect x="92" y="69" width="23" height="23" fill="#AEAEAE"></rect>
+                  <rect x="115" y="46" width="23" height="23" fill="white"></rect>
+                  <rect x="115" y="115" width="23" height="23" fill="white"></rect>
+                  <rect x="115" y="69" width="23" height="23" fill="#D9D9D9"></rect>
+                  <rect x="92" y="46" width="23" height="23" fill="#AEAEAE"></rect>
+                  <rect x="92" y="115" width="23" height="23" fill="#AEAEAE"></rect>
+                  <rect x="92" y="69" width="23" height="23" fill="white"></rect>
+                  <rect x="69" y="46" width="23" height="23" fill="white"></rect>
+                  <rect x="69" y="115" width="23" height="23" fill="white"></rect>
+                  <rect x="69" y="69" width="23" height="23" fill="#D9D9D9"></rect>
+                  <rect x="46" y="46" width="23" height="23" fill="black"></rect>
+                  <rect x="46" y="115" width="23" height="23" fill="black"></rect>
+                  <rect x="46" y="69" width="23" height="23" fill="black"></rect>
+                  <rect x="23" y="46" width="23" height="23" fill="#D9D9D9"></rect>
+                  <rect x="23" y="115" width="23" height="23" fill="#AEAEAE"></rect>
+                  <rect x="23" y="69" width="23" height="23" fill="black"></rect>
+                </svg>
+                <h1 style="font-weight: 900; margin-bottom: 7px;">
+                  Stable Diffusion Demo
+                </h1>
+              </div>
+              <p style="margin-bottom: 10px; font-size: 94%">
+                Stable Diffusion is a state of the art text-to-image model that generates
+                images from text.<br>For faster generation and forthcoming API
+                access you can try
+                <a
+                  href="http://beta.dreamstudio.ai/"
+                  style="text-decoration: underline;"
+                  target="_blank"
+                  >DreamStudio Beta</a
+                >
+              </p>
+            </div>
+        """
+
+
+footer_html = """
+                <div class="footer">
+                    <p>Model by <a href="https://huggingface.co/CompVis" style="text-decoration: underline;" target="_blank">CompVis</a> and <a href="https://huggingface.co/stabilityai" style="text-decoration: underline;" target="_blank">Stability AI</a> - Gradio Demo by 🤗 Hugging Face
+                    </p>
+                </div>
+                <div class="acknowledgments">
+                    <p><h4>LICENSE</h4>
+The model is licensed with a <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" style="text-decoration: underline;" target="_blank">CreativeML Open RAIL-M</a> license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" target="_blank" style="text-decoration: underline;" target="_blank">read the license</a></p>
+                    <p><h4>Biases and content acknowledgment</h4>
+Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the <a href="https://laion.ai/blog/laion-5b/" style="text-decoration: underline;" target="_blank">LAION-5B dataset</a>, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4" style="text-decoration: underline;" target="_blank">model card</a></p>
+               </div>
+           """
+
+css = """
+        .gradio-container {
+            font-family: 'IBM Plex Sans', sans-serif;
+        }
+        .gr-button {
+            color: white;
+            border-color: black;
+            background: black;
+        }
+        input[type='range'] {
+            accent-color: black;
+        }
+        .dark input[type='range'] {
+            accent-color: #dfdfdf;
+        }
+        .container {
+            max-width: 730px;
+            margin: auto;
+            padding-top: 1.5rem;
+        }
+        #gallery {
+            min-height: 22rem;
+            margin-bottom: 15px;
+            margin-left: auto;
+            margin-right: auto;
+            border-bottom-right-radius: .5rem !important;
+            border-bottom-left-radius: .5rem !important;
+        }
+        #gallery>div>.h-full {
+            min-height: 20rem;
+        }
+        .details:hover {
+            text-decoration: underline;
+        }
+        .gr-button {
+            white-space: nowrap;
+        }
+        .gr-button:focus {
+            border-color: rgb(147 197 253 / var(--tw-border-opacity));
+            outline: none;
+            box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
+            --tw-border-opacity: 1;
+            --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
+            --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
+            --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
+            --tw-ring-opacity: .5;
+        }
+        #advanced-btn {
+            font-size: .7rem !important;
+            line-height: 19px;
+            margin-top: 12px;
+            margin-bottom: 12px;
+            padding: 2px 8px;
+            border-radius: 14px !important;
+        }
+        #advanced-options {
+            display: none;
+            margin-bottom: 20px;
+        }
+        .footer {
+            margin-bottom: 45px;
+            margin-top: 35px;
+            text-align: center;
+            border-bottom: 1px solid #e5e5e5;
+        }
+        .footer>p {
+            font-size: .8rem;
+            display: inline-block;
+            padding: 0 10px;
+            transform: translateY(10px);
+            background: white;
+        }
+        .dark .footer {
+            border-color: #303030;
+        }
+        .dark .footer>p {
+            background: #0b0f19;
+        }
+        .acknowledgments h4{
+            margin: 1.25em 0 .25em 0;
+            font-weight: bold;
+            font-size: 115%;
+        }
+"""