Duplicate from Charles-Elena/ControlNet-endpoint

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,115 @@
+---
+license: openrail
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- controlnet
+- endpoints-template
+thumbnail: "https://huggingface.co/philschmid/ControlNet-endpoint/resolve/main/thumbnail.png"
+inference: true
+---
+
+
+# Inference Endpoint for [ControlNet](https://huggingface.co/lllyasviel/ControlNet) using [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)
+
+
+> ControlNet is a neural network structure to control diffusion models by adding extra conditions.
+> Official repository: https://github.com/lllyasviel/ControlNet
+
+---
+
+Blog post: [Controlled text to image generation with Inference Endpoints]()
+
+This repository implements a custom `handler` task for `controlled text-to-image` generation on 🤗 Inference Endpoints. The code for the customized pipeline is in the [handler.py](https://huggingface.co/philschmid/ControlNet-endpoint/blob/main/handler.py).
+
+There is also a [notebook](https://huggingface.co/philschmid/ControlNet-endpoint/blob/main/create_handler.ipynb) included, on how to create the `handler.py`
+
+![sample](thumbnail.png)
+
+
+### expected Request payload
+
+```json
+{
+    "inputs": "A prompt used for image generation",
+    "negative_prompt": "low res, bad anatomy, worst quality, low quality",
+    "controlnet_type": "depth",
+    "image" : "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAABGdBTUEAALGPC",
+}
+```
+
+supported `controlnet_type` are: `canny_edge`, `pose`, `depth`, `scribble`, `segmentation`, `normal`, `hed`, `hough`
+
+below is an example on how to run a request using Python and `requests`.
+
+
+## Use Python to send requests
+
+1. Get image 
+```
+wget https://huggingface.co/datasets/diffusers/test-arrays/resolve/main/stable_diffusion_imgvar/input_image_vermeer.png
+```
+
+2. Use the following code to send a request to the endpoint
+
+```python
+import json
+from typing import List
+import requests as r
+import base64
+from PIL import Image
+from io import BytesIO
+
+ENDPOINT_URL = "" # your endpoint url
+HF_TOKEN = "" # your huggingface token `hf_xxx`
+
+# helper image utils
+def encode_image(image_path):
+  with open(image_path, "rb") as i:
+    b64 = base64.b64encode(i.read())
+  return b64.decode("utf-8")
+
+
+def predict(prompt, image, negative_prompt=None, controlnet_type = "normal"):
+    image = encode_image(image)
+
+    # prepare sample payload
+    request = {"inputs": prompt, "image": image, "negative_prompt": negative_prompt, "controlnet_type": controlnet_type}
+    # headers
+    headers = {
+        "Authorization": f"Bearer {HF_TOKEN}",
+        "Content-Type": "application/json",
+        "Accept": "image/png" # important to get an image back
+    }
+
+    response = r.post(ENDPOINT_URL, headers=headers, json=request)
+    if response.status_code != 200:
+        print(response.text)
+        raise Exception("Prediction failed")
+    img = Image.open(BytesIO(response.content))
+    return img
+
+
+prediction = predict(
+  prompt = "cloudy sky background lush landscape house and green trees, RAW photo (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3",
+  negative_prompt ="lowres, bad anatomy, worst quality, low quality, city, traffic",
+  controlnet_type = "hed",
+  image = "huggingface.png"
+)
+
+prediction.save("result.png")
+```
+
+```
+expected output
+
+![sample](result.png) 
+
+
+[Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543) by Lvmin Zhang and Maneesh Agrawala.
+
+Using the pretrained models we can provide control images (for example, a depth map) to control Stable Diffusion text-to-image generation so that it follows the structure of the depth image and fills in the details.
+
+The abstract of the paper is the following:
+
+We present a neural network structure, ControlNet, to control pretrained large diffusion models to support additional input conditions. The ControlNet learns task-specific conditions in an end-to-end way, and the learning is robust even when the training dataset is small (< 50k). Moreover, training a ControlNet is as fast as fine-tuning a diffusion model, and the model can be trained on a personal devices. Alternatively, if powerful computation clusters are available, the model can scale to large amounts (millions to billions) of data. We report that large diffusion models like Stable Diffusion can be augmented with ControlNets to enable conditional inputs like edge maps, segmentation maps, keypoints, etc. This may enrich the methods to control large diffusion models and further facilitate related applications.

handler.py

@@ -0,0 +1,155 @@
+from typing import  Dict, List, Any
+import base64
+from PIL import Image
+from io import BytesIO
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+#from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, StableDiffusionSafetyChecker
+# import Safety Checker
+from diffusers.pipelines.stable_diffusion import StableDiffusionSafetyChecker
+
+import torch
+
+
+import numpy as np
+import cv2
+import controlnet_hinter
+
+# set device
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+if device.type != 'cuda':
+    raise ValueError("need to run on GPU")
+# set mixed precision dtype
+dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16
+    
+# controlnet mapping for controlnet id and control hinter
+CONTROLNET_MAPPING = {
+    "canny_edge": {
+        "model_id": "lllyasviel/sd-controlnet-canny",
+        "hinter": controlnet_hinter.hint_canny
+    },
+    "pose": {
+        "model_id": "lllyasviel/sd-controlnet-openpose",
+        "hinter": controlnet_hinter.hint_openpose
+    },
+    "depth": {
+        "model_id": "lllyasviel/sd-controlnet-depth",
+        "hinter": controlnet_hinter.hint_depth
+    },
+    "scribble": {
+        "model_id": "lllyasviel/sd-controlnet-scribble",
+        "hinter": controlnet_hinter.hint_scribble,
+    },
+    "segmentation": {
+        "model_id": "lllyasviel/sd-controlnet-seg",
+        "hinter": controlnet_hinter.hint_segmentation,
+    },
+    "normal": {
+        "model_id": "lllyasviel/sd-controlnet-normal",
+        "hinter": controlnet_hinter.hint_normal,
+    },
+    "hed": {
+        "model_id": "lllyasviel/sd-controlnet-hed",
+        "hinter": controlnet_hinter.hint_hed,
+    },
+    "hough": {
+        "model_id": "lllyasviel/sd-controlnet-mlsd",
+        "hinter": controlnet_hinter.hint_hough,
+    }
+}
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        # define default controlnet id and load controlnet
+        self.control_type = "depth"
+        self.controlnet = ControlNetModel.from_pretrained(CONTROLNET_MAPPING[self.control_type]["model_id"],torch_dtype=dtype).to(device)
+
+        #processor = AutoProcessor.from_pretrained("CompVis/stable-diffusion-safety-checker")
+
+        
+        # Load StableDiffusionControlNetPipeline 
+        #self.stable_diffusion_id = "runwayml/stable-diffusion-v1-5"
+        self.stable_diffusion_id = "Lykon/dreamshaper-8"
+#        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(self.stable_diffusion_id, 
+#                                                                      controlnet=self.controlnet, 
+#                                                                      torch_dtype=dtype,
+#                                                                      #safety_checker=None).to(device)
+#                                                                      #processor = AutoProcessor.from_pretrained("CompVis/stable-diffusion-safety-checker")
+#                                                                      #safety_checker = SafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker")
+#                                                                      safety_checker = StableDiffusionSafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker")
+
+#        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
+#            self.stable_diffusion_id, 
+#            controlnet=self.controlnet, 
+#            torch_dtype=dtype,
+#            safety_checker = SafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker")
+#        ).to(device)
+
+
+        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(self.stable_diffusion_id,
+                                                                      controlnet=self.controlnet, 
+                                                                      torch_dtype=dtype,
+                                                                      safety_checker=StableDiffusionSafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker", torch_dtype=dtype)).to("cuda")
+        # Define Generator with seed
+        self.generator = torch.Generator(device=device.type).manual_seed(3)
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        """
+        :param data: A dictionary contains `inputs` and optional `image` field.
+        :return: A dictionary with `image` field contains image in base64.
+        """
+        prompt = data.pop("inputs", None)
+        image = data.pop("image", None)
+        controlnet_type = data.pop("controlnet_type", None)
+        
+        # Check if neither prompt nor image is provided
+        if prompt is None and image is None:
+            return {"error": "Please provide a prompt and base64 encoded image."}
+        
+        # Check if a new controlnet is provided
+        if controlnet_type is not None and controlnet_type != self.control_type:
+            print(f"changing controlnet from {self.control_type} to {controlnet_type} using {CONTROLNET_MAPPING[controlnet_type]['model_id']} model")
+            self.control_type = controlnet_type
+            self.controlnet = ControlNetModel.from_pretrained(CONTROLNET_MAPPING[self.control_type]["model_id"],
+                                                              torch_dtype=dtype).to(device)
+            self.pipe.controlnet = self.controlnet
+        
+        
+        # hyperparamters
+        negatice_prompt = data.pop("negative_prompt", None)
+        num_inference_steps = data.pop("num_inference_steps", 30)
+        guidance_scale = data.pop("guidance_scale", 7.4)
+        negative_prompt = data.pop("negative_prompt", None)
+        height = data.pop("height", None)
+        width = data.pop("width", None)
+        controlnet_conditioning_scale = data.pop("controlnet_conditioning_scale", 1.0)
+        
+        # process image
+        image = self.decode_base64_image(image)
+        #control_image = CONTROLNET_MAPPING[self.control_type]["hinter"](image)
+
+        # run inference pipeline
+        out = self.pipe(
+            prompt=prompt, 
+            negative_prompt=negative_prompt,
+            #image=control_image,
+            image=image,
+            num_inference_steps=num_inference_steps, 
+            guidance_scale=guidance_scale,
+            num_images_per_prompt=1,
+            height=height,
+            width=width,
+            controlnet_conditioning_scale=controlnet_conditioning_scale,
+            generator=self.generator
+        )
+
+        
+        # return first generate PIL image
+        return out.images[0]
+    
+    # helper to decode input image
+    def decode_base64_image(self, image_string):
+        base64_image = base64.b64decode(image_string)
+        buffer = BytesIO(base64_image)
+        image = Image.open(buffer)
+        return image

request.json

@@ -0,0 +1 @@
+{"inputs": "cloudy sky background lush landscape house and green trees, RAW photo (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3", "image": "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", "negative_prompt": "worst quality, city, traffic", "controlnet_type": "depth"}

requirements.txt

@@ -0,0 +1,3 @@
+safetensors 
+opencv-python
+controlnet_hinter==0.0.5