Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+cache/1709866575_76532584.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,6 @@
 ---
-title: FaceID
-emoji: 😻
-colorFrom: green
-colorTo: gray
+title: faceID
+app_file: websockets_api_v1_3_0229_debug_beta.py
 sdk: gradio
-sdk_version: 4.20.1
-app_file: app.py
-pinned: false
+sdk_version: 3.41.2
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

websockets_api_v1_3_0229_debug_beta.py

@@ -0,0 +1,134 @@
+import os
+import random
+import websocket
+import uuid
+import json
+import urllib.request
+import urllib.parse
+import gradio as gr
+from glob import glob
+import requests
+from pathlib import Path
+import base64
+from PIL import Image
+import time
+import io
+
+server_address = "127.0.0.1:8188"
+client_id = str(uuid.uuid4())
+
+
+def queue_prompt(prompt):
+    p = {"prompt": prompt, "client_id": client_id}
+    data = json.dumps(p).encode('utf-8')
+    req =  urllib.request.Request("http://{}/prompt".format(server_address), data=data)
+    return json.loads(urllib.request.urlopen(req).read())
+
+def get_image(filename, subfolder, folder_type):
+    data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
+    url_values = urllib.parse.urlencode(data)
+    with urllib.request.urlopen("http://{}/view?{}".format(server_address, url_values)) as response:
+        return response.read()
+
+def get_history(prompt_id):
+    with urllib.request.urlopen("http://{}/history/{}".format(server_address, prompt_id)) as response:
+        return json.loads(response.read())
+
+
+def get_images(ws, prompt):
+    prompt_id = queue_prompt(prompt)['prompt_id']
+    output_images = {}
+    while True:
+        out = ws.recv()
+        if isinstance(out, str):
+            message = json.loads(out)
+            if message['type'] == 'executing':
+                data = message['data']
+                if data['node'] is None and data['prompt_id'] == prompt_id:
+                    break #Execution is done
+        else:
+            continue #previews are binary data
+
+    history = get_history(prompt_id)[prompt_id]
+    for o in history['outputs']:
+        for node_id in history['outputs']:
+            node_output = history['outputs'][node_id]
+            if 'images' in node_output:
+                images_output = []
+                for image in node_output['images']:
+                    image_data = get_image(image['filename'], image['subfolder'], image['type'])
+                    images_output.append(image_data)
+            output_images[node_id] = images_output
+
+    return output_images
+
+def detect(image):
+    img = Path(image).read_bytes() 
+    rsp = requests.post(f'http://cv.bytedance.net/aipet_head_det/run/predict', json={
+        'data': ['data:image/png;base64,'+
+            base64.b64encode(img).decode('utf-8'),
+        ]
+    })
+
+    return rsp.json()['data'][1]
+
+def clip_save(img_in,coords,path="img.png"):
+
+    img = Image.open(img_in)
+    img2 = img.crop((int(coords[0]), int(coords[1]), int(coords[2]), int(coords[3])))
+    img2.save(path)
+
+
+def load_template(img_in,seed):
+    seed = int(seed)
+    with open(workflow_base,encoding='utf-8') as file:
+        template = json.load(file)
+    template["14"]["inputs"]["image"] = img_in
+    # template["7"]["inputs"]["text"] = animal + templates[style]
+    template["3"]["inputs"]["seed"] = seed if seed > 0 else random.randint(1,1e8)
+    # template["31"]["inputs"]["seed"] = seed if seed > 0 else random.randint(1,1e8)
+    # template["30"]["inputs"]["lora_name"] = loras[style]
+    # template["30"]["inputs"]["strength_model"] = w_lora
+    # template["30"]["inputs"]["strength_clip"] = w_lora
+    # if debug:
+        # print(template["6"]["inputs"]["image"],template["7"]["inputs"]["text"],template["9"]["inputs"]["seed"],template["30"]["inputs"]["lora_name"],template["30"]["inputs"]["strength_model"],template["30"]["inputs"]["strength_clip"])
+    return template
+
+def generate(img_in,seed):
+    seed = int(seed)
+
+    template = load_template(img_in,seed)
+    ws = websocket.WebSocket()
+    ws.connect("ws://{}/ws?clientId={}".format(server_address, client_id))
+    images = get_images(ws, template)
+
+    for node_id in images:
+        for image_data in images[node_id]:
+            image = Image.open(io.BytesIO(image_data))
+            path_out = dir_cache+"/"+str(time.time()).split('.')[0]+"_"+str(template["3"]["inputs"]["seed"])+".png"
+            image.save(path_out)
+
+    return image
+
+if __name__ == '__main__':
+
+
+    workflow_base = "D:/faceID/workflow_api_anime_0306.json"
+    dir_cache = "D:/faceID/cache"
+    seed = -1
+    # debug = True
+    demo = gr.Interface(
+
+        fn = generate,
+        inputs = [
+            gr.Image(type='filepath'),
+            # gr.Textbox(label="自定义品种",value="", info="自定义品种,内部调试使用"),
+            # gr.Radio(["发财麻将","东北大花","情人玫瑰","天使丘比特","爱心丘比特","美式证件照","新年工笔画","新年唐装","新年糖葫芦","宠物礼盒","生日快乐","雪地工笔画","破壳纪念","爱读书的学霸","米其林大厨","疯狂赛车手","工笔画","圣诞树","圣诞雪人","圣诞老人",], label="风格", info="更多风格规划中，敬请期待~"),
+            # gr.Slider(0, 1, value=0.5,step=0.05,label='风格化程度',info='推荐值:低风格化0.3, 中风格化0.5, 高风格化0.7'),
+            gr.Textbox(label="随机种子",value=-1, info="-1为随机种子,大于0时为自定义种子")        
+        ],
+        outputs = ["image"]
+    )
+
+    demo.queue(max_size=2)
+    demo.launch(share=True) 

workflow_api_anime_0306.json

@@ -0,0 +1,194 @@
+{
+  "3": {
+    "inputs": {
+      "seed": 0,
+      "steps": 20,
+      "cfg": 4,
+      "sampler_name": "dpmpp_2m_sde",
+      "scheduler": "karras",
+      "denoise": 1,
+      "model": [
+        "10",
+        0
+      ],
+      "positive": [
+        "6",
+        0
+      ],
+      "negative": [
+        "7",
+        0
+      ],
+      "latent_image": [
+        "5",
+        0
+      ]
+    },
+    "class_type": "KSampler",
+    "_meta": {
+      "title": "KSampler"
+    }
+  },
+  "4": {
+    "inputs": {
+      "ckpt_name": "ghostxl_v10BakedVAE.safetensors"
+    },
+    "class_type": "CheckpointLoaderSimple",
+    "_meta": {
+      "title": "Load Checkpoint"
+    }
+  },
+  "5": {
+    "inputs": {
+      "width": 768,
+      "height": 1024,
+      "batch_size": 1
+    },
+    "class_type": "EmptyLatentImage",
+    "_meta": {
+      "title": "Empty Latent Image"
+    }
+  },
+  "6": {
+    "inputs": {
+      "text": "masterpiece, 8K, best quality, clean background",
+      "clip": [
+        "4",
+        1
+      ]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": {
+      "title": "CLIP Text Encode (Prompt)"
+    }
+  },
+  "7": {
+    "inputs": {
+      "text": "nsfw,blurry, low quality, distorted, photo, frame, naked, horror,embedding:EasyNegative",
+      "clip": [
+        "4",
+        1
+      ]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": {
+      "title": "CLIP Text Encode (Prompt)"
+    }
+  },
+  "8": {
+    "inputs": {
+      "samples": [
+        "3",
+        0
+      ],
+      "vae": [
+        "4",
+        2
+      ]
+    },
+    "class_type": "VAEDecode",
+    "_meta": {
+      "title": "VAE Decode"
+    }
+  },
+  "9": {
+    "inputs": {
+      "filename_prefix": "ComfyUI",
+      "images": [
+        "8",
+        0
+      ]
+    },
+    "class_type": "SaveImage",
+    "_meta": {
+      "title": "Save Image"
+    }
+  },
+  "10": {
+    "inputs": {
+      "weight": 1,
+      "noise": 0,
+      "weight_type": "original",
+      "start_at": 0,
+      "end_at": 1,
+      "faceid_v2": true,
+      "weight_v2": 1,
+      "unfold_batch": false,
+      "ipadapter": [
+        "11",
+        0
+      ],
+      "clip_vision": [
+        "41",
+        0
+      ],
+      "insightface": [
+        "13",
+        0
+      ],
+      "image": [
+        "14",
+        0
+      ],
+      "model": [
+        "39",
+        0
+      ]
+    },
+    "class_type": "IPAdapterApplyFaceID",
+    "_meta": {
+      "title": "Apply IPAdapter FaceID"
+    }
+  },
+  "11": {
+    "inputs": {
+      "ipadapter_file": "ip-adapter-faceid-plusv2_sdxl.bin"
+    },
+    "class_type": "IPAdapterModelLoader",
+    "_meta": {
+      "title": "Load IPAdapter Model"
+    }
+  },
+  "13": {
+    "inputs": {
+      "provider": "CUDA"
+    },
+    "class_type": "InsightFaceLoader",
+    "_meta": {
+      "title": "Load InsightFace"
+    }
+  },
+  "14": {
+    "inputs": {
+      "image": "comfyworkflows_f0942efd-fb40-422b-8cd4-cbaa39529fab (3).png",
+      "upload": "image"
+    },
+    "class_type": "LoadImage",
+    "_meta": {
+      "title": "Load Image"
+    }
+  },
+  "39": {
+    "inputs": {
+      "lora_name": "ip-adapter-faceid-plusv2_sdxl_lora.safetensors",
+      "strength_model": 1,
+      "model": [
+        "4",
+        0
+      ]
+    },
+    "class_type": "LoraLoaderModelOnly",
+    "_meta": {
+      "title": "LoraLoaderModelOnly"
+    }
+  },
+  "41": {
+    "inputs": {
+      "clip_name": "ipadpter1.5.safetensors"
+    },
+    "class_type": "CLIPVisionLoader",
+    "_meta": {
+      "title": "Load CLIP Vision"
+    }
+  }
+}