File size: 6,271 Bytes
ccaf67e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 |
import websocket # NOTE: websocket-client (https://github.com/websocket-client/websocket-client)
import uuid
import json
import urllib.request
import urllib.parse
import random
import logging
from config import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["COMFYUI"])
from pydantic import BaseModel
from typing import Optional
COMFYUI_DEFAULT_PROMPT = """
{
"3": {
"inputs": {
"seed": 0,
"steps": 20,
"cfg": 8,
"sampler_name": "euler",
"scheduler": "normal",
"denoise": 1,
"model": [
"4",
0
],
"positive": [
"6",
0
],
"negative": [
"7",
0
],
"latent_image": [
"5",
0
]
},
"class_type": "KSampler",
"_meta": {
"title": "KSampler"
}
},
"4": {
"inputs": {
"ckpt_name": "model.safetensors"
},
"class_type": "CheckpointLoaderSimple",
"_meta": {
"title": "Load Checkpoint"
}
},
"5": {
"inputs": {
"width": 512,
"height": 512,
"batch_size": 1
},
"class_type": "EmptyLatentImage",
"_meta": {
"title": "Empty Latent Image"
}
},
"6": {
"inputs": {
"text": "Prompt",
"clip": [
"4",
1
]
},
"class_type": "CLIPTextEncode",
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"7": {
"inputs": {
"text": "Negative Prompt",
"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"
}
}
}
"""
def queue_prompt(prompt, client_id, base_url):
log.info("queue_prompt")
p = {"prompt": prompt, "client_id": client_id}
data = json.dumps(p).encode("utf-8")
req = urllib.request.Request(f"{base_url}/prompt", data=data)
return json.loads(urllib.request.urlopen(req).read())
def get_image(filename, subfolder, folder_type, base_url):
log.info("get_image")
data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
url_values = urllib.parse.urlencode(data)
with urllib.request.urlopen(f"{base_url}/view?{url_values}") as response:
return response.read()
def get_image_url(filename, subfolder, folder_type, base_url):
log.info("get_image")
data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
url_values = urllib.parse.urlencode(data)
return f"{base_url}/view?{url_values}"
def get_history(prompt_id, base_url):
log.info("get_history")
with urllib.request.urlopen(f"{base_url}/history/{prompt_id}") as response:
return json.loads(response.read())
def get_images(ws, prompt, client_id, base_url):
prompt_id = queue_prompt(prompt, client_id, base_url)["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, base_url)[prompt_id]
for o in history["outputs"]:
for node_id in history["outputs"]:
node_output = history["outputs"][node_id]
if "images" in node_output:
for image in node_output["images"]:
url = get_image_url(
image["filename"], image["subfolder"], image["type"], base_url
)
output_images.append({"url": url})
return {"data": output_images}
class ImageGenerationPayload(BaseModel):
prompt: str
negative_prompt: Optional[str] = ""
steps: Optional[int] = None
seed: Optional[int] = None
width: int
height: int
n: int = 1
cfg_scale: Optional[float] = None
sampler: Optional[str] = None
scheduler: Optional[str] = None
sd3: Optional[bool] = None
def comfyui_generate_image(
model: str, payload: ImageGenerationPayload, client_id, base_url
):
ws_url = base_url.replace("http://", "ws://").replace("https://", "wss://")
comfyui_prompt = json.loads(COMFYUI_DEFAULT_PROMPT)
if payload.cfg_scale:
comfyui_prompt["3"]["inputs"]["cfg"] = payload.cfg_scale
if payload.sampler:
comfyui_prompt["3"]["inputs"]["sampler"] = payload.sampler
if payload.scheduler:
comfyui_prompt["3"]["inputs"]["scheduler"] = payload.scheduler
if payload.sd3:
comfyui_prompt["5"]["class_type"] = "EmptySD3LatentImage"
comfyui_prompt["4"]["inputs"]["ckpt_name"] = model
comfyui_prompt["5"]["inputs"]["batch_size"] = payload.n
comfyui_prompt["5"]["inputs"]["width"] = payload.width
comfyui_prompt["5"]["inputs"]["height"] = payload.height
# set the text prompt for our positive CLIPTextEncode
comfyui_prompt["6"]["inputs"]["text"] = payload.prompt
comfyui_prompt["7"]["inputs"]["text"] = payload.negative_prompt
if payload.steps:
comfyui_prompt["3"]["inputs"]["steps"] = payload.steps
comfyui_prompt["3"]["inputs"]["seed"] = (
payload.seed if payload.seed else random.randint(0, 18446744073709551614)
)
try:
ws = websocket.WebSocket()
ws.connect(f"{ws_url}/ws?clientId={client_id}")
log.info("WebSocket connection established.")
except Exception as e:
log.exception(f"Failed to connect to WebSocket server: {e}")
return None
try:
images = get_images(ws, comfyui_prompt, client_id, base_url)
except Exception as e:
log.exception(f"Error while receiving images: {e}")
images = None
ws.close()
return images
|