Create app.py

app.py

@@ -0,0 +1,84 @@
+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 PIL import Image
+from diffusers import FlaxStableDiffusionControlNetPipeline, FlaxControlNetModel
+import cv2
+
+def create_key(seed=0):
+    return jax.random.PRNGKey(seed)
+
+def canny_filter(image):
+    gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    blurred_image = cv2.GaussianBlur(gray_image, (5, 5), 0)
+    edges_image = cv2.Canny(blurred_image, 50, 200)
+    return edges_image
+
+# load control net and stable diffusion v1-5
+controlnet, controlnet_params = FlaxControlNetModel.from_pretrained(
+    "tsungtao/controlnet-mlsd-202305011046", from_flax=True, dtype=jnp.bfloat16
+)
+pipe, params = FlaxStableDiffusionControlNetPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, revision="flax", dtype=jnp.bfloat16
+)
+
+def infer(prompts, negative_prompts, image):
+    params["controlnet"] = controlnet_params
+    
+    num_samples = 1 #jax.device_count()
+    rng = create_key(0)
+    rng = jax.random.split(rng, jax.device_count())
+    im = canny_filter(image)
+    canny_image = Image.fromarray(im)
+    
+    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:])))
+    return output_images
+
+title = "ControlNet MLSD"
+description = "This is a demo on ControlNet MLSD."
+examples = [["living room with TV", "fan", "image_01.jpg"],
+            ["a living room with hardwood floors and a flat screen tv", "sea", "image_02.jpg"],
+            ["a living room with a fireplace and a view of the ocean", "pendant", "image_03.jpg"]
+           ]
+
+with gr.Blocks(css=".gradio-container {background: url('file=sky.jpg')}") as demo:
+    gr.Interface(infer, inputs=["text", "text", "image"], outputs="gallery", title = title, description = description, examples = examples, theme='gradio/soft')
+
+    gr.Markdown(
+    """
+    * * *
+    * [Dataset](https://huggingface.co/datasets/tsungtao/diffusers-testing)
+    * [Diffusers model](https://huggingface.co/runwayml/stable-diffusion-v1-5)
+    * [Training Report](https://wandb.ai/tsungtao0311/controlnet-mlsd-202305011046/runs/ezfn6bkz?workspace=user-tsungtao0311)
+    """)
+
+    with gr.Accordion("Open for More!"):
+        gr.Markdown("Look at me...")
+    
+    gr.Markdown("* * *")
+    gr.Markdown(""" <img src='https://huggingface.co/spaces/tsungtao/tsungtao-controlnet-mlsd-202305011046/blob/main/test.png' /> """)
+
+
+demo.launch()