feat: add new app

README.md

@@ -5,7 +5,7 @@ colorFrom: yellow
 colorTo: purple
 sdk: gradio
 sdk_version: 5.31.0
-app_file: app.py
+app_file: app_bak.py
 pinned: false
 license: mit
 short_description: 'EEEM068 Spring 2025 Applied Machine Learning Project'

app.py

@@ -1,26 +1,154 @@
 # -*- coding: UTF-8 -*-
 """
-@Time : 28/05/2025 10:06
+@Time : 28/05/2025 16:29
 @Author : xiaoguangliang
 @File : app.py
 @Project : Faice_text2face
 """
 import gradio as gr
-from stable_diffusion_inference import inference
 
+from stable_diffusion_inference import inference, MAX_SEED, MAX_IMAGE_SIZE
+from utils import timer
 
-# def greet(name):
-#     return "Hello " + name + "!!"
-#
-#
-# demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+examples = [
+    "A capybara wearing a suit holding a sign that reads Hello World",
+    "A serene mountain lake at sunset with cherry blossoms floating on the water",
+    "A magical crystal dragon with iridescent scales in a glowing forest",
+    "A Victorian steampunk teapot with intricate brass gears and rose gold accents",
+    "A futuristic neon cityscape with flying cars and holographic billboards",
+    "A red panda painter creating a masterpiece with tiny paws in an art studio",
+]
 
+css = """
+body {
+    background: linear-gradient(135deg, #f9e2e6 0%, #e8f3fc 50%, #e2f9f2 100%);
+    background-attachment: fixed;
+    min-height: 100vh;
+}
+#col-container {
+    margin: 0 auto;
+    max-width: 640px;
+    background-color: rgba(255, 255, 255, 0.85);
+    border-radius: 16px;
+    box-shadow: 0 8px 16px rgba(0, 0, 0, 0.1);
+    padding: 24px;
+    backdrop-filter: blur(10px);
+}
+.gradio-container {
+    background: transparent !important;
+}
+.gr-button-primary {
+    background: linear-gradient(90deg, #6b9dfc, #8c6bfc) !important;
+    border: none !important;
+    transition: all 0.3s ease;
+}
+.gr-button-primary:hover {
+    transform: translateY(-2px);
+    box-shadow: 0 5px 15px rgba(108, 99, 255, 0.3);
+}
+.gr-form {
+    border-radius: 12px;
+    background-color: rgba(255, 255, 255, 0.7);
+}
+.gr-accordion {
+    border-radius: 12px;
+    overflow: hidden;
+}
+h1 {
+    background: linear-gradient(90deg, #6b9dfc, #8c6bfc);
+    -webkit-background-clip: text;
+    -webkit-text-fill-color: transparent;
+    font-weight: 800;
+}
+"""
+
+with gr.Blocks(theme="apriel", css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(" # TensorArt Stable Diffusion 3.5 Large TurboX")
+        gr.Markdown(
+            "[8-step distilled turbo model](https://huggingface.co/tensorart/stable-diffusion-3.5-large-TurboX)")
+        with gr.Row():
+            prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+
+            run_button = gr.Button("Run", scale=0, variant="primary")
+
+        result = gr.Image(label="Result", show_label=False)
+
+        with gr.Accordion("Advanced Settings", open=False):
+            negative_prompt = gr.Text(
+                label="Negative prompt",
+                max_lines=1,
+                placeholder="Enter a negative prompt",
+            )
+
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=0,
+            )
+
+            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+
+            with gr.Row():
+                width = gr.Slider(
+                    label="Width",
+                    minimum=512,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
+
+                height = gr.Slider(
+                    label="Height",
+                    minimum=512,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
 
-def text2face(prompt):
-    image = inference(prompt)
-    return image
+            with gr.Row():
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.0,
+                    maximum=7.5,
+                    step=0.1,
+                    value=1.5,
+                )
 
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=8,
+                )
 
-demo = gr.Interface(fn=text2face, inputs="text", outputs="image")
+        gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=inference,
+                    cache_examples=True, cache_mode="lazy")
+    gr.on(
+        triggers=[run_button.click, prompt.submit],
+        fn=inference,
+        inputs=[
+            prompt,
+            negative_prompt,
+            seed,
+            randomize_seed,
+            width,
+            height,
+            guidance_scale,
+            num_inference_steps,
+        ],
+        outputs=[result, seed],
+    )
 
-demo.launch()
+if __name__ == "__main__":
+    with timer("All tasks"):
+        demo.launch(mcp_server=True)

app_bak.py

@@ -0,0 +1,28 @@
+# -*- coding: UTF-8 -*-
+"""
+@Time : 28/05/2025 10:06
+@Author : xiaoguangliang
+@File : app_bak.py
+@Project : Faice_text2face
+"""
+import gradio as gr
+from stable_diffusion_inference import inference
+from utils import timer
+
+
+# def greet(name):
+#     return "Hello " + name + "!!"
+#
+#
+# demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+
+
+def text2face(prompt):
+    image = inference(prompt)
+    return image
+
+
+with timer("All tasks"):
+    demo = gr.Interface(fn=text2face, inputs="text", outputs="image")
+
+demo.launch()

requirements.txt

@@ -21,6 +21,7 @@ huggingface-hub==0.32.2
 idna==3.10
 importlib_metadata==8.7.0
 Jinja2==3.1.6
+loguru==0.7.3
 markdown-it-py==3.0.0
 MarkupSafe==3.0.2
 mdurl==0.1.2
@@ -31,7 +32,7 @@ orjson==3.10.18
 packaging==25.0
 pandas==2.2.3
 pillow==11.2.1
-psutil==7.0.0
+psutil==5.9.8
 pydantic==2.11.5
 pydantic_core==2.33.2
 pydub==0.25.1
@@ -50,6 +51,7 @@ semantic-version==2.10.0
 shellingham==1.5.4
 six==1.17.0
 sniffio==1.3.1
+spaces==0.36.0
 starlette==0.46.2
 sympy==1.14.0
 tokenizers==0.21.1
@@ -66,4 +68,4 @@ tzdata==2025.2
 urllib3==2.4.0
 uvicorn==0.34.2
 websockets==15.0.1
-zipp==3.22.0
+zipp==3.22.0

stable_diffusion_inference.py

@@ -6,27 +6,63 @@
 @Project : Faice_text2face
 """
 import torch
+import random
+import numpy as np
 from diffusers import StableDiffusionPipeline
 from accelerate import Accelerator
+import gradio as gr
+import spaces
 
 model_path = 'Ngene787/Faice_text2face'
 
+accelerator = Accelerator(mixed_precision="fp16", gradient_accumulation_steps=1)
+pipe = StableDiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float16,
+                                               low_cpu_mem_usage=True)
 
-def inference(prompt):
-    accelerator = Accelerator(mixed_precision="fp16", gradient_accumulation_steps=1)
-    pipe = StableDiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float16,
-                                                   low_cpu_mem_usage=True)
-    # pipe = pipe.to("cuda")
-    pipe = accelerator.prepare(pipe)
+device = "cuda" if torch.cuda.is_available() else "cpu"
+if torch.cuda.is_available():
+    torch_dtype = torch.float16
+else:
+    torch_dtype = torch.float32
+pipe = pipe.to(device)
 
-    # Enable memory-efficient attention
-    # pipe.enable_xformers_memory_efficient_attention()
+pipe = accelerator.prepare(pipe)
+# Enable memory-efficient attention
+# pipe.enable_xformers_memory_efficient_attention()
 
-    # Enable attention slicing
-    pipe.enable_attention_slicing()
+# Enable attention slicing
+pipe.enable_attention_slicing()
 
-    # Enable VAE slicing
-    pipe.enable_vae_slicing()
+# Enable VAE slicing
+pipe.enable_vae_slicing()
 
-    image = pipe(prompt).images[0]
-    return image
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 256
+
+
+@spaces.GPU(duration=65)
+def inference(prompt,
+              negative_prompt="",
+              seed=42,
+              randomize_seed=False,
+              width=MAX_IMAGE_SIZE,
+              height=MAX_IMAGE_SIZE,
+              guidance_scale=1.5,
+              num_inference_steps=8,
+              progress=gr.Progress(track_tqdm=True), ):
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+
+    generator = torch.Generator().manual_seed(seed)
+
+    image = pipe(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        width=width,
+        height=height,
+        generator=generator,
+    ).images[0]
+    # image = pipe(prompt).images[0]
+    return image, seed

utils.py

@@ -0,0 +1,22 @@
+# -*- coding: UTF-8 -*-
+"""
+@Time : 28/05/2025 16:17
+@Author : xiaoguangliang
+@File : utils.py
+@Project : Faice_text2face
+"""
+import time
+from contextlib import contextmanager
+
+
+@contextmanager
+def timer(msg="all tasks"):
+    """
+    Calculate the time of running
+    @return:
+    """
+    startTime = time.time()
+    yield
+    endTime = time.time()
+    # print(f'The time cost for {msg}：{round(1000.0 * (endTime - startTime), 2)}, ms')
+    print(f"The time cost for {msg}：", round((endTime - startTime) / 60, 2), "minutes")