app.py

import gradio as gr
import jax
import numpy as np
import jax.numpy as jnp
from flax.jax_utils import replicate
from flax.training.common_utils import shard
#from diffusers.utils import load_image
from diffusers.utils.testing_utils import load_image
from PIL import Image
from diffusers import FlaxStableDiffusionControlNetPipeline, FlaxControlNetModel

def image_grid(imgs, rows, cols):
    w, h = imgs[0].size
    grid = Image.new("RGB", size=(cols * w, rows * h))
    for i, img in enumerate(imgs):
        grid.paste(img, box=(i % cols * w, i // cols * h))
    return grid

def create_key(seed=0):
    return jax.random.PRNGKey(seed)

rng = create_key(0)

canny_image = load_image(
    "https://huggingface.co/datasets/YiYiXu/test-doc-assets/resolve/main/blog_post_cell_10_output_0.jpeg"
)

prompts = "a living room with tv, sea, window"
negative_prompts = "fan "

controlnet, controlnet_params = FlaxControlNetModel.from_pretrained(
    "tsungtao/controlnet-mlsd-202305011046", from_flax=True, dtype=jnp.float32
)

pipe, params = FlaxStableDiffusionControlNetPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, revision="flax", dtype=jnp.float32
)

params["controlnet"] = controlnet_params

num_samples = jax.device_count()
rng = jax.random.split(rng, jax.device_count())

prompt_ids = pipe.prepare_text_inputs([prompts] * num_samples)
negative_prompt_ids = pipe.prepare_text_inputs([negative_prompts] * num_samples)
processed_image = pipe.prepare_image_inputs([canny_image] * num_samples)

p_params = replicate(params)
prompt_ids = shard(prompt_ids)
negative_prompt_ids = shard(negative_prompt_ids)
processed_image = shard(processed_image)

output = pipe(
    prompt_ids=prompt_ids,
    image=processed_image,
    params=p_params,
    prng_seed=rng,
    num_inference_steps=50,
    neg_prompt_ids=negative_prompt_ids,
    jit=True,
).images

output_images = pipe.numpy_to_pil(np.asarray(output.reshape((num_samples,) + output.shape[-3:])))
output_images = image_grid(output_images, num_samples // 4, 4)
output_images.save("tao/image.png")

#gr.Interface.load("models/tsungtao/controlnet-mlsd-202305011046").launch()
def infer(prompt, negative_prompt, image):
    # implement your inference function here
    return output_image

gr.Interface(fn = infer, inputs = ["text", "text", "image"], outputs = "image").launch()