Update app.py

app.py

@@ -1,71 +1,43 @@
-"""
-Adapted from https://huggingface.co/spaces/stabilityai/stable-diffusion
-"""
-
-from tensorflow import keras
+import gradio as gr
+#import torch
+#from torch import autocast // only for GPU
 
-keras.mixed_precision.set_global_policy("mixed_float16")
+from PIL import Image
 
-import time
+import os
+MY_SECRET_TOKEN=os.environ.get('HF_TOKEN_SD')
 
-import gradio as gr
-import keras_cv
+from diffusers import StableDiffusionPipeline
+#from diffusers import StableDiffusionImg2ImgPipeline
 
-from constants import css, examples, img_height, img_width, num_images_to_gen
-from share_btn import community_icon_html, loading_icon_html, share_js
+print("hello sylvain")
 
-# Load model.
-weights_path = keras.utils.get_file(
-    origin="https://huggingface.co/sayakpaul/kerascv_sd_pokemon_finetuned/resolve/main/ckpt_epochs_72_res_512_mp_True.h5",
-    file_hash="10b20bd27912d1da904dafe8c576351c2f373546f446591aeff00d816d701a6e"
-)
-pokemon_model = keras_cv.models.StableDiffusion(
-    img_width=img_width, img_height=img_height
-)
-pokemon_model.to(device)
-pokemon_model.diffusion_model.load_weights(weights_path)
-
-pokemon_model.diffusion_model.compile(jit_compile=True)
-pokemon_model.decoder.compile(jit_compile=True)
-pokemon_model.text_encoder.compile(jit_compile=True)
+YOUR_TOKEN=MY_SECRET_TOKEN
 
 device="cpu"
 
-# Warm-up the model.
-#_ = pokemon_model.text_to_image("Teddy bear", batch_size=num_images_to_gen)
+pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_auth_token=YOUR_TOKEN)
+pipe.to(device)
+
+gallery = gr.Gallery(label="Generated images", show_label=False, elem_id="gallery").style(grid=[2], height="auto")
 
+def infer(prompt): 
+    
+    #image = pipe(prompt, init_image=init_image)["sample"][0]
+    images_list = pipe([prompt] * 4)
+    images = []
+    safe_image = Image.open(r"unsafe.png")
+    for i, image in enumerate(images_list["images"]):
+        if(images_list["nsfw_content_detected"][i]):
+            images.append(safe_image)
+        else:
+            images.append(image)
+    
+    return images
 
-def generate_image_fn(prompt: str, unconditional_guidance_scale: int) -> list:
-    start_time = time.time()
-    # `images is an `np.ndarray`. So we convert it to a list of ndarrays.
-    # Each ndarray represents a generated image.
-    # Reference: https://gradio.app/docs/#gallery
-    images = pokemon_model.text_to_image(
-        prompt,
-        batch_size=num_images_to_gen,
-        unconditional_guidance_scale=unconditional_guidance_scale,
-    )
-    end_time = time.time()
-    print(f"Time taken: {end_time - start_time} seconds.")
-    return [image for image in images]
+print("Great sylvain ! Everything is working fine !")
 
+title="Stable Diffusion CPU"
+description="Stable Diffusion example using CPU and HF token. <br />Warning: Slow process... ~5/10 min inference time. <b>NSFW filter enabled.</b>" 
 
-description = "This Space demonstrates a fine-tuned Stable Diffusion model. You can use it for generating custom pokemons. To get started, either enter a prompt and pick one from the examples below. For details on the fine-tuning procedure, refer to [this repository](https://github.com/sayakpaul/stable-diffusion-keras-ft/)."
-article = "This Space leverages a T4 GPU to run the predictions. We use mixed-precision to speed up the inference latency. We further use XLA to carve out maximum performance from TensorFlow."
-gr.Interface(
-    generate_image_fn,
-    inputs=[
-        gr.Textbox(
-            label="Enter your prompt",
-            max_lines=1,
-            placeholder="cute Sundar Pichai creature",
-        ),
-        gr.Slider(value=40, minimum=8, maximum=50, step=1),
-    ],
-    outputs=gr.Gallery().style(grid=[2], height="auto"),
-    title="Generate custom pokemons",
-    description=description,
-    article=article,
-    examples=[["cute Sundar Pichai creature", 40], ["Hello kitty", 40]],
-    allow_flagging=False,
-).launch(enable_queue=True)
+gr.Interface(fn=infer, inputs="text", outputs=gallery,title=title,description=description).queue(max_size=10).launch(enable_queue=True)