Spaces:
Paused
Paused
""" | |
Adapted from https://huggingface.co/spaces/stabilityai/stable-diffusion | |
""" | |
from tensorflow import keras | |
keras.mixed_precision.set_global_policy("mixed_float16") | |
import time | |
import gradio as gr | |
import keras_cv | |
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 | |
# Load model. | |
weights_path = keras.utils.get_file( | |
origin="https://huggingface.co/andrew27/kerascv_clothing_finetuned/resolve/main/ckpt_epoch_96.h5", | |
file_hash="4b4348297aa9853ff9dc4da7f52dcb240210564400f164e5155e5f4dc1866626" | |
) | |
pokemon_model = keras_cv.models.StableDiffusion( | |
img_width=img_width, img_height=img_height | |
) | |
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) | |
# Warm-up the model. | |
#_ = pokemon_model.text_to_image("Teddy bear", batch_size=num_images_to_gen) | |
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] | |
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.outputs.Image(type="pil"),gr.outputs.Image(type="pil")], | |
title="Generate custom pokemons", | |
description=description, | |
article=article, | |
examples=[["cute Sundar Pichai creature", 40], ["Hello kitty", 40]], | |
allow_flagging=False, | |
).launch() |