Upload 13 files

README.md

@@ -8,6 +8,7 @@ sdk_version: 4.39.0
 app_file: app.py
 pinned: false
 short_description: Text-to-Image
+license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,71 +1,37 @@
 import gradio as gr
 from model import models
 from multit2i import (
-    load_models,
-    infer_multi,
-    infer_multi_random,
-    save_gallery_images,
-    change_model,
-    get_model_info_md,
-    loaded_models,
-    get_positive_prefix,
-    get_positive_suffix,
-    get_negative_prefix,
-    get_negative_suffix,
-    get_recom_prompt_type,
-    set_recom_prompt_preset,
-    get_tag_type,
+    load_models, infer_fn, infer_rand_fn, save_gallery,
+    change_model, warm_model, get_model_info_md, loaded_models,
+    get_positive_prefix, get_positive_suffix, get_negative_prefix, get_negative_suffix,
+    get_recom_prompt_type, set_recom_prompt_preset, get_tag_type,
 )
 from tagger.tagger import (
-    predict_tags_wd,
-    remove_specific_prompt,
-    convert_danbooru_to_e621_prompt,
-    insert_recom_prompt,
-    compose_prompt_to_copy,
+    predict_tags_wd, remove_specific_prompt, convert_danbooru_to_e621_prompt,
+    insert_recom_prompt, compose_prompt_to_copy,
 )
 from tagger.fl2sd3longcap import predict_tags_fl2_sd3
-from tagger.v2 import (
-    V2_ALL_MODELS,
-    v2_random_prompt,
-)
+from tagger.v2 import V2_ALL_MODELS, v2_random_prompt
 from tagger.utils import (
-    V2_ASPECT_RATIO_OPTIONS,
-    V2_RATING_OPTIONS,
-    V2_LENGTH_OPTIONS,
-    V2_IDENTITY_OPTIONS,
+    V2_ASPECT_RATIO_OPTIONS, V2_RATING_OPTIONS,
+    V2_LENGTH_OPTIONS, V2_IDENTITY_OPTIONS,
 )
 
 
-load_models(models, 5)
-#load_models(models, 20) # Fetching 20 models at the same time. default: 5
-
+max_images = 8
+load_models(models)
 
 css = """
-#model_info { text-align: center; }
+.model_info { text-align: center; }
+.output { width=112px; height=112px; !important; }
+.gallery { width=100%; min_height=768px; !important; }
 """
 
-with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", css=css) as demo:
+with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", fill_width=True, css=css) as demo:
     with gr.Column(): 
-        with gr.Accordion("Advanced settings", open=False):
-            with gr.Accordion("Recommended Prompt", open=False):
-                recom_prompt_preset = gr.Radio(label="Set Presets", choices=get_recom_prompt_type(), value="Common")
-                with gr.Row():
-                    positive_prefix = gr.CheckboxGroup(label="Use Positive Prefix", choices=get_positive_prefix(), value=[])
-                    positive_suffix = gr.CheckboxGroup(label="Use Positive Suffix", choices=get_positive_suffix(), value=["Common"])
-                    negative_prefix = gr.CheckboxGroup(label="Use Negative Prefix", choices=get_negative_prefix(), value=[], visible=False)
-                    negative_suffix = gr.CheckboxGroup(label="Use Negative Suffix", choices=get_negative_suffix(), value=["Common"], visible=False)
-            with gr.Accordion("Prompt Transformer", open=False):
-                v2_rating = gr.Radio(label="Rating", choices=list(V2_RATING_OPTIONS), value="sfw")
-                v2_aspect_ratio = gr.Radio(label="Aspect ratio", info="The aspect ratio of the image.", choices=list(V2_ASPECT_RATIO_OPTIONS), value="square", visible=False)
-                v2_length = gr.Radio(label="Length", info="The total length of the tags.", choices=list(V2_LENGTH_OPTIONS), value="long")
-                v2_identity = gr.Radio(label="Keep identity", info="How strictly to keep the identity of the character or subject. If you specify the detail of subject in the prompt, you should choose `strict`. Otherwise, choose `none` or `lax`. `none` is very creative but sometimes ignores the input prompt.", choices=list(V2_IDENTITY_OPTIONS), value="lax")                    
-                v2_ban_tags = gr.Textbox(label="Ban tags", info="Tags to ban from the output.", placeholder="alternate costumen, ...", value="censored")
-                v2_tag_type = gr.Radio(label="Tag Type", info="danbooru for common, e621 for Pony.", choices=["danbooru", "e621"], value="danbooru", visible=False)
-                v2_model = gr.Dropdown(label="Model", choices=list(V2_ALL_MODELS.keys()), value=list(V2_ALL_MODELS.keys())[0])
-                v2_copy = gr.Button(value="Copy to clipboard", size="sm", interactive=False)
-            with gr.Accordion("Model", open=True):
-                model_name = gr.Dropdown(label="Select Model", show_label=False, choices=list(loaded_models.keys()), value=list(loaded_models.keys())[0], allow_custom_value=True)
-                model_info = gr.Markdown(value=get_model_info_md(list(loaded_models.keys())[0]), elem_id="model_info")
+        with gr.Group():
+            model_name = gr.Dropdown(label="Select Model", choices=list(loaded_models.keys()), value=list(loaded_models.keys())[0], allow_custom_value=True)
+            model_info = gr.Markdown(value=get_model_info_md(list(loaded_models.keys())[0]), elem_classes="model_info")
         with gr.Group():
             with gr.Accordion("Prompt from Image File", open=False):
                 tagger_image = gr.Image(label="Input image", type="pil", sources=["upload", "clipboard"], height=256)
@@ -82,59 +48,82 @@ with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", css=css) as demo:
                 v2_series = gr.Textbox(label="Series", placeholder="vocaloid", scale=2)
                 random_prompt = gr.Button(value="Extend Prompt 🎲", size="sm", scale=1)
                 clear_prompt = gr.Button(value="Clear Prompt 🗑️", size="sm", scale=1)
-            prompt = gr.Text(label="Prompt", lines=1, max_lines=8, placeholder="1girl, solo, ...", show_copy_button=True)
+            prompt = gr.Text(label="Prompt", lines=2, max_lines=8, placeholder="1girl, solo, ...", show_copy_button=True)
             neg_prompt = gr.Text(label="Negative Prompt", lines=1, max_lines=8, placeholder="", visible=False)
+            with gr.Accordion("Recommended Prompt", open=False):
+                recom_prompt_preset = gr.Radio(label="Set Presets", choices=get_recom_prompt_type(), value="Common")
+                with gr.Row():
+                    positive_prefix = gr.CheckboxGroup(label="Use Positive Prefix", choices=get_positive_prefix(), value=[])
+                    positive_suffix = gr.CheckboxGroup(label="Use Positive Suffix", choices=get_positive_suffix(), value=["Common"])
+                    negative_prefix = gr.CheckboxGroup(label="Use Negative Prefix", choices=get_negative_prefix(), value=[], visible=False)
+                    negative_suffix = gr.CheckboxGroup(label="Use Negative Suffix", choices=get_negative_suffix(), value=["Common"], visible=False)
+            with gr.Accordion("Prompt Transformer", open=False):
+                v2_rating = gr.Radio(label="Rating", choices=list(V2_RATING_OPTIONS), value="sfw")
+                v2_aspect_ratio = gr.Radio(label="Aspect ratio", info="The aspect ratio of the image.", choices=list(V2_ASPECT_RATIO_OPTIONS), value="square", visible=False)
+                v2_length = gr.Radio(label="Length", info="The total length of the tags.", choices=list(V2_LENGTH_OPTIONS), value="long")
+                v2_identity = gr.Radio(label="Keep identity", info="How strictly to keep the identity of the character or subject. If you specify the detail of subject in the prompt, you should choose `strict`. Otherwise, choose `none` or `lax`. `none` is very creative but sometimes ignores the input prompt.", choices=list(V2_IDENTITY_OPTIONS), value="lax")                    
+                v2_ban_tags = gr.Textbox(label="Ban tags", info="Tags to ban from the output.", placeholder="alternate costumen, ...", value="censored")
+                v2_tag_type = gr.Radio(label="Tag Type", info="danbooru for common, e621 for Pony.", choices=["danbooru", "e621"], value="danbooru", visible=False)
+                v2_model = gr.Dropdown(label="Model", choices=list(V2_ALL_MODELS.keys()), value=list(V2_ALL_MODELS.keys())[0])
+                v2_copy = gr.Button(value="Copy to clipboard", size="sm", interactive=False)
+        image_num = gr.Slider(label="Number of images", minimum=1, maximum=max_images, value=1, step=1, interactive=True, scale=1)
         with gr.Row():
             run_button = gr.Button("Generate Image", scale=6)
             random_button = gr.Button("Random Model 🎲", scale=3)
-            image_num = gr.Number(label="Count", minimum=1, maximum=16, value=1, step=1, interactive=True, scale=1)
-        results = gr.Gallery(label="Gallery", interactive=False, show_download_button=True, show_share_button=False,
-                              container=True, format="png", object_fit="contain")
-        image_files = gr.Files(label="Download", interactive=False)
-        clear_results = gr.Button("Clear Gallery / Download")
-    examples = gr.Examples(
-        examples = [
-            ["souryuu asuka langley, 1girl, neon genesis evangelion, plugsuit, pilot suit, red bodysuit, sitting, crossing legs, black eye patch, cat hat, throne, symmetrical, looking down, from bottom, looking at viewer, outdoors"],
-            ["sailor moon, magical girl transformation, sparkles and ribbons, soft pastel colors, crescent moon motif, starry night sky background, shoujo manga style"],
-            ["kafuu chino, 1girl, solo"],
-            ["1girl"],
-            ["beautiful sunset"],
-        ],
-        inputs=[prompt],
-    )
-    gr.Markdown(
-        f"""This demo was created in reference to the following demos.
-- [Nymbo/Flood](https://huggingface.co/spaces/Nymbo/Flood).
-- [Yntec/ToyWorldXL](https://huggingface.co/spaces/Yntec/ToyWorldXL).
-            """
-    )
-    gr.DuplicateButton(value="Duplicate Space")
+            stop_button = gr.Button('Stop', interactive=False, scale=1)
+    with gr.Column(): 
+        with gr.Group():
+            with gr.Row():
+                output = [gr.Image(label='', elem_classes="output", type="filepath", format=".png",
+                          show_download_button=True, show_share_button=False, show_label=False,
+                          interactive=False, min_width=80, visible=True) for _ in range(max_images)]
+        with gr.Group():
+            results = gr.Gallery(label="Gallery", elem_classes="gallery", interactive=False, show_download_button=True, show_share_button=False,
+                                 container=True, format="png", object_fit="cover", columns=2, rows=2)
+            image_files = gr.Files(label="Download", interactive=False)
+            clear_results = gr.Button("Clear Gallery / Download 🗑️")
+    with gr.Column(): 
+        examples = gr.Examples(
+            examples = [
+                ["souryuu asuka langley, 1girl, neon genesis evangelion, plugsuit, pilot suit, red bodysuit, sitting, crossing legs, black eye patch, cat hat, throne, symmetrical, looking down, from bottom, looking at viewer, outdoors"],
+                ["sailor moon, magical girl transformation, sparkles and ribbons, soft pastel colors, crescent moon motif, starry night sky background, shoujo manga style"],
+                ["kafuu chino, 1girl, solo"],
+                ["1girl"],
+                ["beautiful sunset"],
+            ],
+            inputs=[prompt],
+        )
+        gr.Markdown(
+            f"""This demo was created in reference to the following demos.<br>
+    [Nymbo/Flood](https://huggingface.co/spaces/Nymbo/Flood), 
+    [Yntec/ToyWorldXL](https://huggingface.co/spaces/Yntec/ToyWorldXL), 
+    [Yntec/Diffusion80XX](https://huggingface.co/spaces/Yntec/Diffusion80XX).
+                """
+        )
+        gr.DuplicateButton(value="Duplicate Space")
 
-    model_name.change(change_model, [model_name], [model_info], queue=False, show_api=False)
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer_multi,
-        inputs=[prompt, neg_prompt, results, image_num, model_name,
-                 positive_prefix, positive_suffix, negative_prefix, negative_suffix],
-        outputs=[results],
-        queue=True,
-        show_progress="full",
-        show_api=True,
-    ).success(save_gallery_images, [results], [results, image_files], queue=False, show_api=False)
-    gr.on(
-        triggers=[random_button.click],
-        fn=infer_multi_random,
-        inputs=[prompt, neg_prompt, results, image_num,
-                 positive_prefix, positive_suffix, negative_prefix, negative_suffix],
-        outputs=[results],
-        queue=True,
-        show_progress="full",
-        show_api=True,
-    ).success(save_gallery_images, [results], [results, image_files], queue=False, show_api=False)
-    clear_prompt.click(lambda: (None, None, None), None, [prompt, v2_series, v2_character], queue=False, show_api=False)
+    gr.on(triggers=[run_button.click, prompt.submit, random_button.click], fn=lambda: gr.update(interactive=True), inputs=None, outputs=stop_button, show_api=False)
+    model_name.change(change_model, [model_name], [model_info], queue=False, show_api=False)\
+    .success(warm_model, [model_name], None, queue=True, show_api=False)
+    for i, o in enumerate(output):
+        img_i = gr.Number(i, visible=False)
+        image_num.change(lambda i, n: gr.update(visible = (i < n)), [img_i, image_num], o, show_api=False)
+        gen_event = gr.on(triggers=[run_button.click, prompt.submit],
+         fn=lambda i, n, m, t1, t2, l1, l2, l3, l4: infer_fn(m, t1, t2, l1, l2, l3, l4) if (i < n) else None,
+         inputs=[img_i, image_num, model_name, prompt, neg_prompt, positive_prefix, positive_suffix, negative_prefix, negative_suffix],
+         outputs=[o], queue=True, show_api=False)
+        gen_event2 = gr.on(triggers=[random_button.click],
+         fn=lambda i, n, m, t1, t2, l1, l2, l3, l4: infer_rand_fn(m, t1, t2, l1, l2, l3, l4) if (i < n) else None,
+         inputs=[img_i, image_num, model_name, prompt, neg_prompt, positive_prefix, positive_suffix, negative_prefix, negative_suffix],
+         outputs=[o], queue=True, show_api=False)
+        o.change(save_gallery, [o, results], [results, image_files], show_api=False)
+        stop_button.click(lambda: gr.update(interactive=False), None, stop_button, cancels=[gen_event, gen_event2], show_api=False)
+
+    clear_prompt.click(lambda: None, None, [prompt], queue=False, show_api=False)
     clear_results.click(lambda: (None, None), None, [results, image_files], queue=False, show_api=False)
     recom_prompt_preset.change(set_recom_prompt_preset, [recom_prompt_preset],
      [positive_prefix, positive_suffix, negative_prefix, negative_suffix], queue=False, show_api=False)
+
     random_prompt.click(
         v2_random_prompt, [prompt, v2_series, v2_character, v2_rating, v2_aspect_ratio, v2_length,
           v2_identity, v2_ban_tags, v2_model], [prompt, v2_series, v2_character], show_api=False,

multit2i.py

@@ -80,33 +80,36 @@ def get_t2i_model_info_dict(repo_id: str):
     return info
 
 
-def save_gallery_images(images, progress=gr.Progress(track_tqdm=True)):
+def rename_image(image_path: str | None, model_name: str):
+    from PIL import Image
     from datetime import datetime, timezone, timedelta
-    progress(0, desc="Updating gallery...")
+    if image_path is None: return None
     dt_now = datetime.now(timezone(timedelta(hours=9)))
-    basename = dt_now.strftime('%Y%m%d_%H%M%S_')
-    i = 1
-    if not images: return images
-    output_images = []
-    output_paths = []
-    for image in images:
-        filename = f'{image[1]}_{basename}{str(i)}.png'
-        i += 1
-        oldpath = Path(image[0])
-        newpath = oldpath
-        try:
-            if oldpath.stem == "image" and oldpath.exists():
-                newpath = oldpath.resolve().rename(Path(filename).resolve())
-        except Exception as e:
-           print(e)
-           pass
-        finally:
-            output_paths.append(str(newpath))
-            output_images.append((str(newpath), str(filename)))
-    progress(1, desc="Gallery updated.")
-    return gr.update(value=output_images), gr.update(value=output_paths)
+    filename = f"{model_name.split('/')[-1]}_{dt_now.strftime('%Y%m%d_%H%M%S')}.png"
+    try:
+        if Path(image_path).exists():
+            png_path = "image.png"
+            Image.open(image_path).convert('RGBA').save(png_path, "PNG")
+            new_path = str(Path(png_path).resolve().rename(Path(filename).resolve()))
+            return new_path
+        else:
+            return None
+    except Exception as e:
+        print(e)
+        return None
+
+
+def save_gallery(image_path: str | None, images: list[tuple] | None):
+    if images is None: images = []
+    files = [i[0] for i in images]
+    if image_path is None: return images, files
+    files.insert(0, str(image_path))
+    images.insert(0, (str(image_path), Path(image_path).stem))
+    return images, files
 
 
+# https://github.com/gradio-app/gradio/blob/main/gradio/external.py
+# https://huggingface.co/docs/huggingface_hub/package_reference/inference_client
 def load_from_model(model_name: str, hf_token: str = None):
     import httpx
     import huggingface_hub
@@ -122,7 +125,7 @@ def load_from_model(model_name: str, hf_token: str = None):
             f"Could not find model: {model_name}. If it is a private or gated model, please provide your Hugging Face access token (https://huggingface.co/settings/tokens) as the argument for the `hf_token` parameter."
         )
     headers["X-Wait-For-Model"] = "true"
-    client = huggingface_hub.InferenceClient(model=model_name, headers=headers, token=hf_token)
+    client = huggingface_hub.InferenceClient(model=model_name, headers=headers, token=hf_token, timeout=600)
     inputs = gr.components.Textbox(label="Input")
     outputs = gr.components.Image(label="Output")
     fn = client.text_to_image
@@ -161,27 +164,9 @@ def load_model(model_name: str):
     return loaded_models[model_name]
 
 
-async def async_load_models(models: list, limit: int=5):
-    sem = asyncio.Semaphore(limit)
-    async def async_load_model(model: str):
-        async with sem:
-           try:
-               return await asyncio.to_thread(load_model, model)
-           except Exception as e:
-               print(e)
-    tasks = [asyncio.create_task(async_load_model(model)) for model in models]
-    return await asyncio.gather(*tasks, return_exceptions=True)
-
-
-def load_models(models: list, limit: int=5):
-    loop = asyncio.new_event_loop()
-    try:
-        loop.run_until_complete(async_load_models(models, limit))
-    except Exception as e:
-        print(e)
-        pass
-    finally:
-        loop.close()
+def load_models(models: list):
+    for model in models:
+        load_model(model)
 
 
 positive_prefix = {
@@ -295,56 +280,73 @@ def change_model(model_name: str):
     return get_model_info_md(model_name)
 
 
-def infer(prompt: str, neg_prompt: str, model_name: str):
-    from PIL import Image
+def warm_model(model_name: str):
+    model = load_model(model_name)
+    if model:
+        try:
+            print(f"Warming model: {model_name}")
+            model(" ")
+        except Exception as e:
+            print(e)
+
+
+async def infer(model_name: str, prompt: str, neg_prompt: str, timeout: float):
     import random
-    seed = ""
+    noise = ""
     rand = random.randint(1, 500)
     for i in range(rand):
-        seed += " "
-    caption = model_name.split("/")[-1]
+        noise += " "
+    model = load_model(model_name)
+    if not model: return None
+    task = asyncio.create_task(asyncio.to_thread(model, f'{prompt} {noise}'))
+    await asyncio.sleep(0)
     try:
-        model = load_model(model_name)
-        if not model: return (Image.Image(), None)
-        image_path = model(prompt + seed)
-        image = Image.open(image_path).convert('RGBA')
-    except Exception as e:
+        result = await asyncio.wait_for(task, timeout=timeout)
+    except (Exception, asyncio.TimeoutError) as e:
         print(e)
-        return (Image.Image(), None)
-    return (image, caption)
-
-
-async def infer_multi(prompt: str, neg_prompt: str, results: list, image_num: float, model_name: str,
-                 pos_pre: list = [], pos_suf: list = [], neg_pre: list = [], neg_suf: list = [], progress=gr.Progress(track_tqdm=True)):
-    from tqdm.asyncio import tqdm_asyncio
-    image_num = int(image_num)
-    images = results if results else []
-    prompt, neg_prompt = recom_prompt(prompt, neg_prompt, pos_pre, pos_suf, neg_pre, neg_suf)
-    tasks = [asyncio.to_thread(infer, prompt, neg_prompt, model_name) for i in range(image_num)]
-    #results = await asyncio.gather(*tasks, return_exceptions=True)
-    results = await tqdm_asyncio.gather(*tasks)
-    if not results: results = []
-    for result in results:
+        print(f"Task timed out: {model_name}")
+        if not task.done(): task.cancel()
+        result = None
+    if task.done() and result is not None:
         with lock:
-            if result and result[1]: images.append(result)
-        yield images
+            image = rename_image(result, model_name)
+        return image
+    return None
+
+
+infer_timeout = 300
+def infer_fn(model_name: str, prompt: str, neg_prompt: str,
+             pos_pre: list = [], pos_suf: list = [], neg_pre: list = [], neg_suf: list = []):
+    if model_name == 'NA':
+        return None
+    try:
+        prompt, neg_prompt = recom_prompt(prompt, neg_prompt, pos_pre, pos_suf, neg_pre, neg_suf)
+        loop = asyncio.new_event_loop()
+        result = loop.run_until_complete(infer(model_name, prompt, neg_prompt, infer_timeout))
+    except (Exception, asyncio.CancelledError) as e:
+        print(e)
+        print(f"Task aborted: {model_name}")
+        result = None
+    finally:
+        loop.close()
+    return result
 
 
-async def infer_multi_random(prompt: str, neg_prompt: str, results: list, image_num: float, 
-                 pos_pre: list = [], pos_suf: list = [], neg_pre: list = [], neg_suf: list = [], progress=gr.Progress(track_tqdm=True)):
-    from tqdm.asyncio import tqdm_asyncio
+def infer_rand_fn(model_name_dummy: str, prompt: str, neg_prompt: str,
+             pos_pre: list = [], pos_suf: list = [], neg_pre: list = [], neg_suf: list = []):
     import random
-    image_num = int(image_num)
-    images = results if results else []
+    if model_name_dummy == 'NA':
+        return None
     random.seed()
-    model_names = random.choices(list(loaded_models.keys()), k = image_num)
-    prompt, neg_prompt = recom_prompt(prompt, neg_prompt, pos_pre, pos_suf, neg_pre, neg_suf)
-    tasks = [asyncio.to_thread(infer, prompt, neg_prompt, model_name) for model_name in model_names]
-    #results = await asyncio.gather(*tasks, return_exceptions=True)
-    results = await tqdm_asyncio.gather(*tasks)
-    if not results: results = []
-    for result in results:
-        with lock:
-            if result and result[1]: images.append(result)
-        yield images
-
+    model_name = random.choice(list(loaded_models.keys()))
+    try:
+        prompt, neg_prompt = recom_prompt(prompt, neg_prompt, pos_pre, pos_suf, neg_pre, neg_suf)
+        loop = asyncio.new_event_loop()
+        result = loop.run_until_complete(infer(model_name, prompt, neg_prompt, infer_timeout))
+    except (Exception, asyncio.CancelledError) as e:
+        print(e)
+        print(f"Task aborted: {model_name}")
+        result = None
+    finally:
+        loop.close()
+    return result