update app [.]

app.py

@@ -0,0 +1,437 @@
+import os
+import json
+import copy
+import time
+import requests
+import random
+import logging
+import numpy as np
+import spaces
+from typing import Any, Dict, List, Optional, Union
+
+import torch
+from PIL import Image
+import gradio as gr
+
+from diffusers import (
+    DiffusionPipeline,
+    AutoPipelineForImage2Image,
+    FlowMatchEulerDiscreteScheduler
+)
+
+from huggingface_hub import (
+    hf_hub_download,
+    HfFileSystem,
+    ModelCard,
+    snapshot_download)
+
+from diffusers.utils import load_image
+from typing import Iterable
+from gradio.themes import Soft
+from gradio.themes.utils import colors, fonts, sizes
+
+# --- THEME DEFINITION ---
+colors.steel_blue = colors.Color(
+    name="steel_blue",
+    c50="#EBF3F8",
+    c100="#D3E5F0",
+    c200="#A8CCE1",
+    c300="#7DB3D2",
+    c400="#529AC3",
+    c500="#4682B4",
+    c600="#3E72A0",
+    c700="#36638C",
+    c800="#2E5378",
+    c900="#264364",
+    c950="#1E3450",
+)
+
+class SteelBlueTheme(Soft):
+    def __init__(
+        self,
+        *,
+        primary_hue: colors.Color | str = colors.gray,
+        secondary_hue: colors.Color | str = colors.steel_blue,
+        neutral_hue: colors.Color | str = colors.slate,
+        text_size: sizes.Size | str = sizes.text_lg,
+        font: fonts.Font | str | Iterable[fonts.Font | str] = (
+            fonts.GoogleFont("Outfit"), "Arial", "sans-serif",
+        ),
+        font_mono: fonts.Font | str | Iterable[fonts.Font | str] = (
+            fonts.GoogleFont("IBM Plex Mono"), "ui-monospace", "monospace",
+        ),
+    ):
+        super().__init__(
+            primary_hue=primary_hue,
+            secondary_hue=secondary_hue,
+            neutral_hue=neutral_hue,
+            text_size=text_size,
+            font=font,
+            font_mono=font_mono,
+        )
+        super().set(
+            background_fill_primary="*primary_50",
+            background_fill_primary_dark="*primary_900",
+            body_background_fill="linear-gradient(135deg, *primary_200, *primary_100)",
+            body_background_fill_dark="linear-gradient(135deg, *primary_900, *primary_800)",
+            button_primary_text_color="white",
+            button_primary_text_color_hover="white",
+            button_primary_background_fill="linear-gradient(90deg, *secondary_500, *secondary_600)",
+            button_primary_background_fill_hover="linear-gradient(90deg, *secondary_600, *secondary_700)",
+            button_primary_background_fill_dark="linear-gradient(90deg, *secondary_600, *secondary_800)",
+            button_primary_background_fill_hover_dark="linear-gradient(90deg, *secondary_500, *secondary_500)",
+            button_secondary_text_color="black",
+            button_secondary_text_color_hover="white",
+            button_secondary_background_fill="linear-gradient(90deg, *primary_300, *primary_300)",
+            button_secondary_background_fill_hover="linear-gradient(90deg, *primary_400, *primary_400)",
+            button_secondary_background_fill_dark="linear-gradient(90deg, *primary_500, *primary_600)",
+            button_secondary_background_fill_hover_dark="linear-gradient(90deg, *primary_500, *primary_500)",
+            slider_color="*secondary_500",
+            slider_color_dark="*secondary_600",
+            block_title_text_weight="600",
+            block_border_width="3px",
+            block_shadow="*shadow_drop_lg",
+            button_primary_shadow="*shadow_drop_lg",
+            button_large_padding="11px",
+            color_accent_soft="*primary_100",
+            block_label_background_fill="*primary_200",
+        )
+
+steel_blue_theme = SteelBlueTheme()
+
+# --- LORA DEFINITIONS ---
+loras = [
+    {
+        "image": "https://huggingface.co/Shakker-Labs/AWPortrait-Z/resolve/main/images/example.png",
+        "title": "AWPortrait-Z",
+        "repo": "Shakker-Labs/AWPortrait-Z",
+        "weights": "AWPortrait-Z.safetensors",
+        "trigger_word": "Portrait"    
+    },
+    {
+        "image": "https://huggingface.co/ostris/z_image_turbo_childrens_drawings/resolve/main/images/1764433591828__000003000_2.jpg",
+        "title": "Childrens Drawings",
+        "repo": "ostris/z_image_turbo_childrens_drawings",
+        "weights": "z_image_turbo_childrens_drawings.safetensors",
+        "trigger_word": "Children Drawings"    
+    },
+]
+
+# --- MODEL LOADING ---
+dtype = torch.bfloat16
+device = "cuda" if torch.cuda.is_available() else "cpu"
+base_model = "Tongyi-MAI/Z-Image-Turbo"
+
+print(f"Loading {base_model}...")
+
+pipe = DiffusionPipeline.from_pretrained(
+    base_model,
+    torch_dtype=dtype,
+)
+pipe.to(device)
+
+# Initialize Image-to-Image pipeline sharing components with the main pipeline
+pipe_i2i = AutoPipelineForImage2Image.from_pipe(pipe)
+
+MAX_SEED = 2**32-1
+
+class calculateDuration:
+    def __init__(self, activity_name=""):
+        self.activity_name = activity_name
+
+    def __enter__(self):
+        self.start_time = time.time()
+        return self
+    
+    def __exit__(self, exc_type, exc_value, traceback):
+        self.end_time = time.time()
+        self.elapsed_time = self.end_time - self.start_time
+        if self.activity_name:
+            print(f"Elapsed time for {self.activity_name}: {self.elapsed_time:.6f} seconds")
+        else:
+            print(f"Elapsed time: {self.elapsed_time:.6f} seconds")
+
+def update_selection(evt: gr.SelectData, width, height):
+    selected_lora = loras[evt.index]
+    new_placeholder = f"Type a prompt for {selected_lora['title']}"
+    lora_repo = selected_lora["repo"]
+    updated_text = f"### Selected: [{lora_repo}](https://huggingface.co/{lora_repo}) ✅"
+    if "aspect" in selected_lora:
+        if selected_lora["aspect"] == "portrait":
+            width = 768
+            height = 1024
+        elif selected_lora["aspect"] == "landscape":
+            width = 1024
+            height = 768
+        else:
+            width = 1024
+            height = 1024
+    return (
+        gr.update(placeholder=new_placeholder),
+        updated_text,
+        evt.index,
+        width,
+        height,
+    )
+
+@spaces.GPU
+def generate_image(prompt_mash, steps, seed, cfg_scale, width, height, lora_scale, progress):
+    pipe.to("cuda")
+    generator = torch.Generator(device="cuda").manual_seed(seed)
+    
+    with calculateDuration("Generating image"):
+        image = pipe(
+            prompt=prompt_mash,
+            num_inference_steps=steps,
+            guidance_scale=cfg_scale,
+            width=width,
+            height=height,
+            generator=generator,
+            joint_attention_kwargs={"scale": lora_scale},
+            output_type="pil",
+        ).images[0]
+        yield image
+
+def generate_image_to_image(prompt_mash, image_input_path, image_strength, steps, cfg_scale, width, height, lora_scale, seed):
+    generator = torch.Generator(device="cuda").manual_seed(seed)
+    pipe_i2i.to("cuda")
+    image_input = load_image(image_input_path)
+    final_image = pipe_i2i(
+        prompt=prompt_mash,
+        image=image_input,
+        strength=image_strength,
+        num_inference_steps=steps,
+        guidance_scale=cfg_scale,
+        width=width,
+        height=height,
+        generator=generator,
+        joint_attention_kwargs={"scale": lora_scale},
+        output_type="pil",
+    ).images[0]
+    return final_image 
+
+@spaces.GPU
+def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_index, randomize_seed, seed, width, height, lora_scale, progress=gr.Progress(track_tqdm=True)):
+    if selected_index is None:
+        raise gr.Error("You must select a LoRA before proceeding.🧨")
+    
+    selected_lora = loras[selected_index]
+    lora_path = selected_lora["repo"]
+    trigger_word = selected_lora["trigger_word"]
+    
+    if(trigger_word):
+        if "trigger_position" in selected_lora:
+            if selected_lora["trigger_position"] == "prepend":
+                prompt_mash = f"{trigger_word} {prompt}"
+            else:
+                prompt_mash = f"{prompt} {trigger_word}"
+        else:
+            prompt_mash = f"{trigger_word} {prompt}"
+    else:
+        prompt_mash = prompt
+
+    with calculateDuration("Unloading LoRA"):
+        pipe.unload_lora_weights()
+        pipe_i2i.unload_lora_weights()
+        
+    # LoRA weights flow
+    with calculateDuration(f"Loading LoRA weights for {selected_lora['title']}"):
+        pipe_to_use = pipe_i2i if image_input is not None else pipe
+        weight_name = selected_lora.get("weights", None)
+        
+        try:
+            pipe_to_use.load_lora_weights(
+                lora_path, 
+                weight_name=weight_name, 
+                low_cpu_mem_usage=True
+            )
+        except Exception as e:
+            print(f"Error loading LoRA: {e}")
+            raise gr.Error(f"Failed to load LoRA: {str(e)}")
+            
+    with calculateDuration("Randomizing seed"):
+        if randomize_seed:
+            seed = random.randint(0, MAX_SEED)
+            
+    if(image_input is not None):
+        final_image = generate_image_to_image(prompt_mash, image_input, image_strength, steps, cfg_scale, width, height, lora_scale, seed)
+        yield final_image, seed, gr.update(visible=False)
+    else:
+        # Standard generation
+        image_generator = generate_image(prompt_mash, steps, seed, cfg_scale, width, height, lora_scale, progress)
+        
+        final_image = None
+        # We process the generator (even if it yields once)
+        for image in image_generator:
+            final_image = image
+            yield image, seed, gr.update(visible=False)
+
+def get_huggingface_safetensors(link):
+    split_link = link.split("/")
+    if(len(split_link) == 2):
+        model_card = ModelCard.load(link)
+        base_model_meta = model_card.data.get("base_model")
+        print(f"Base model metadata: {base_model_meta}")
+  
+        # Note: We relax the check here slightly to allow models compatible with Turbo/Flux
+        # or we just rely on try/catch during loading.
+            
+        image_path = model_card.data.get("widget", [{}])[0].get("output", {}).get("url", None)
+        trigger_word = model_card.data.get("instance_prompt", "")
+        image_url = f"https://huggingface.co/{link}/resolve/main/{image_path}" if image_path else None
+        fs = HfFileSystem()
+        safetensors_name = None
+        try:
+            list_of_files = fs.ls(link, detail=False)
+            for file in list_of_files:
+                if(file.endswith(".safetensors")):
+                    safetensors_name = file.split("/")[-1]
+                if (not image_url and file.lower().endswith((".jpg", ".jpeg", ".png", ".webp"))):
+                    image_elements = file.split("/")
+                    image_url = f"https://huggingface.co/{link}/resolve/main/{image_elements[-1]}"
+        except Exception as e:
+            print(e)
+            gr.Warning(f"You didn't include a link neither a valid Hugging Face repository with a *.safetensors LoRA")
+            raise Exception(f"You didn't include a link neither a valid Hugging Face repository with a *.safetensors LoRA")
+        return split_link[1], link, safetensors_name, trigger_word, image_url
+
+def check_custom_model(link):
+    if(link.startswith("https://")):
+        if(link.startswith("https://huggingface.co") or link.startswith("https://www.huggingface.co")):
+            link_split = link.split("huggingface.co/")
+            return get_huggingface_safetensors(link_split[1])
+    else: 
+        return get_huggingface_safetensors(link)
+
+def add_custom_lora(custom_lora):
+    global loras
+    if(custom_lora):
+        try:
+            title, repo, path, trigger_word, image = check_custom_model(custom_lora)
+            print(f"Loaded custom LoRA: {repo}")
+            card = f'''
+            <div class="custom_lora_card">
+              <span>Loaded custom LoRA:</span>
+              <div class="card_internal">
+                <img src="{image}" />
+                <div>
+                    <h3>{title}</h3>
+                    <small>{"Using: <code><b>"+trigger_word+"</code></b> as the trigger word" if trigger_word else "No trigger word found. If there's a trigger word, include it in your prompt"}<br></small>
+                </div>
+              </div>
+            </div>
+            '''
+            existing_item_index = next((index for (index, item) in enumerate(loras) if item['repo'] == repo), None)
+            if(not existing_item_index):
+                new_item = {
+                    "image": image,
+                    "title": title,
+                    "repo": repo,
+                    "weights": path,
+                    "trigger_word": trigger_word
+                }
+                print(new_item)
+                existing_item_index = len(loras)
+                loras.append(new_item)
+        
+            return gr.update(visible=True, value=card), gr.update(visible=True), gr.Gallery(selected_index=None), f"Custom: {path}", existing_item_index, trigger_word
+        except Exception as e:
+            gr.Warning(f"Invalid LoRA: either you entered an invalid link, or incompatible LoRA")
+            return gr.update(visible=True, value=f"Invalid LoRA: {str(e)}"), gr.update(visible=False), gr.update(), "", None, ""
+    else:
+        return gr.update(visible=False), gr.update(visible=False), gr.update(), "", None, ""
+
+def remove_custom_lora():
+    return gr.update(visible=False), gr.update(visible=False), gr.update(), "", None, ""
+
+run_lora.zerogpu = True
+
+css = '''
+#gen_btn{height: 100%}
+#gen_column{align-self: stretch}
+#title{text-align: center}
+#title h1{font-size: 3em; display:inline-flex; align-items:center}
+#title img{width: 100px; margin-right: 0.5em}
+#gallery .grid-wrap{height: 10vh}
+#lora_list{background: var(--block-background-fill);padding: 0 1em .3em; font-size: 90%}
+.card_internal{display: flex;height: 100px;margin-top: .5em}
+.card_internal img{margin-right: 1em}
+.styler{--form-gap-width: 0px !important}
+#progress{height:30px}
+#progress .generating{display:none}
+.progress-container {width: 100%;height: 30px;background-color: #f0f0f0;border-radius: 15px;overflow: hidden;margin-bottom: 20px}
+.progress-bar {height: 100%;background-color: #4f46e5;width: calc(var(--current) / var(--total) * 100%);transition: width 0.5s ease-in-out}
+'''
+
+with gr.Blocks(delete_cache=(60, 60)) as demo:
+    title = gr.HTML(
+        """<h1>Z-Image-Turbo LoRA Studio ⚡</h1>""",
+        elem_id="title",
+    )
+    selected_index = gr.State(None)
+    with gr.Row():
+        with gr.Column(scale=3):
+            prompt = gr.Textbox(label="Prompt", lines=1, placeholder="✦︎ Choose the LoRA and type the prompt ")
+        with gr.Column(scale=1, elem_id="gen_column"):
+            generate_button = gr.Button("Generate", variant="primary", elem_id="gen_btn")
+    with gr.Row():
+        with gr.Column():
+            selected_info = gr.Markdown("")
+            gallery = gr.Gallery(
+                [(item["image"], item["title"]) for item in loras],
+                label="Z-Image-Turbo LoRAs",
+                allow_preview=False,
+                columns=3,
+                elem_id="gallery",
+            )
+            with gr.Group():
+                custom_lora = gr.Textbox(label="Enter Custom LoRA", placeholder="Shakker-Labs/AWPortrait-Z")
+                gr.Markdown("[Check the list of Z-Image-Turbo LoRA's](https://huggingface.co/models?other=base_model:adapter:Tongyi-MAI/Z-Image-Turbo)", elem_id="lora_list")
+            custom_lora_info = gr.HTML(visible=False)
+            custom_lora_button = gr.Button("Remove custom LoRA", visible=False)
+        with gr.Column():
+            progress_bar = gr.Markdown(elem_id="progress",visible=False)
+            result = gr.Image(label="Generated Image", format="png")
+
+    with gr.Row():
+        with gr.Accordion("Advanced Settings", open=False):
+            with gr.Row():
+                input_image = gr.Image(label="Input image", type="filepath")
+                image_strength = gr.Slider(label="Denoise Strength", info="Lower means more image influence", minimum=0.1, maximum=1.0, step=0.01, value=0.75)
+            with gr.Column():
+                with gr.Row():
+                    cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, step=0.5, value=3.5)
+                    steps = gr.Slider(label="Steps", minimum=1, maximum=50, step=1, value=9)
+                
+                with gr.Row():
+                    width = gr.Slider(label="Width", minimum=256, maximum=1536, step=64, value=1024)
+                    height = gr.Slider(label="Height", minimum=256, maximum=1536, step=64, value=1024)
+                
+                with gr.Row():
+                    randomize_seed = gr.Checkbox(True, label="Randomize seed")
+                    seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0, randomize=True)
+                    lora_scale = gr.Slider(label="LoRA Scale", minimum=0, maximum=3, step=0.01, value=0.95)
+
+    gallery.select(
+        update_selection,
+        inputs=[width, height],
+        outputs=[prompt, selected_info, selected_index, width, height]
+    )
+    custom_lora.input(
+        add_custom_lora,
+        inputs=[custom_lora],
+        outputs=[custom_lora_info, custom_lora_button, gallery, selected_info, selected_index, prompt]
+    )
+    custom_lora_button.click(
+        remove_custom_lora,
+        outputs=[custom_lora_info, custom_lora_button, gallery, selected_info, selected_index, custom_lora]
+    )
+    gr.on(
+        triggers=[generate_button.click, prompt.submit],
+        fn=run_lora,
+        inputs=[prompt, input_image, image_strength, cfg_scale, steps, selected_index, randomize_seed, seed, width, height, lora_scale],
+        outputs=[result, seed, progress_bar]
+    )
+
+demo.queue()
+demo.launch(theme=steel_blue_theme, css=css, mcp_server=True, ssr_mode=False, show_error=True)