Skip to main content

[a/BizyAir](https://github.com/siliconflow/BizyAir) Comfy Nodes that can run in any environment.

Project description

Server Mode

export BIZYAIR_API_KEY="your api key"
export BIZYAIR_SERVER_MODE=1
import json
import os
from urllib import request

BIZYAIR_API_KEY=os.getenv("BIZYAIR_API_KEY", "")

prompt_text = """
{
  "36": {
    "inputs": {
      "clip_name1": "t5xxl_fp16.safetensors",
      "clip_name2": "clip_l.safetensors",
      "type": "flux"
    },
    "class_type": "BizyAir_DualCLIPLoader",
    "_meta": {
      "title": "☁️BizyAir DualCLIPLoader"
    }
  },
  "37": {
    "inputs": {
      "text": "close up photo of a rabbit, forest in spring, haze, halation, bloom, dramatic atmosphere, centred, rule of thirds, 200mm 1.4f macro shot",
      "clip": [
        "36",
        0
      ]
    },
    "class_type": "BizyAir_CLIPTextEncode",
    "_meta": {
      "title": "☁️BizyAir CLIP Text Encode (Prompt)"
    }
  },
  "47": {
    "inputs": {
      "model": [
        "48",
        0
      ],
      "conditioning": [
        "37",
        0
      ]
    },
    "class_type": "BizyAir_BasicGuider",
    "_meta": {
      "title": "☁️BizyAir BasicGuider"
    }
  },
  "48": {
    "inputs": {
      "unet_name": "flux/pixelwave-flux1-dev.safetensors",
      "weight_dtype": "default"
    },
    "class_type": "BizyAir_UNETLoader",
    "_meta": {
      "title": "☁️BizyAir Load Diffusion Model"
    }
  },
  "50": {
    "inputs": {
      "noise": [
        "59",
        0
      ],
      "guider": [
        "47",
        0
      ],
      "sampler": [
        "60",
        0
      ],
      "sigmas": [
        "58",
        0
      ],
      "latent_image": [
        "66",
        0
      ]
    },
    "class_type": "BizyAir_SamplerCustomAdvanced",
    "_meta": {
      "title": "☁️BizyAir SamplerCustomAdvanced"
    }
  },
  "54": {
    "inputs": {
      "samples": [
        "50",
        0
      ],
      "vae": [
        "55",
        0
      ]
    },
    "class_type": "BizyAir_VAEDecode",
    "_meta": {
      "title": "☁️BizyAir VAE Decode"
    }
  },
  "55": {
    "inputs": {
      "vae_name": "flux/ae.sft"
    },
    "class_type": "BizyAir_VAELoader",
    "_meta": {
      "title": "☁️BizyAir Load VAE"
    }
  },
  "56": {
    "inputs": {
      "images": [
        "54",
        0
      ]
    },
    "class_type": "PreviewImage",
    "_meta": {
      "title": "预览图像"
    }
  },
  "58": {
    "inputs": {
      "scheduler": "simple",
      "steps": 20,
      "denoise": 1,
      "model": [
        "48",
        0
      ]
    },
    "class_type": "BizyAir_BasicScheduler",
    "_meta": {
      "title": "☁️BizyAir BasicScheduler"
    }
  },
  "59": {
    "inputs": {
      "noise_seed": 0
    },
    "class_type": "BizyAir_RandomNoise",
    "_meta": {
      "title": "☁️BizyAir RandomNoise"
    }
  },
  "60": {
    "inputs": {
      "sampler_name": "euler"
    },
    "class_type": "BizyAir_KSamplerSelect",
    "_meta": {
      "title": "☁️BizyAir KSamplerSelect"
    }
  },
  "66": {
    "inputs": {
      "width": 1024,
      "height": 1024,
      "batch_size": 1
    },
    "class_type": "EmptySD3LatentImage",
    "_meta": {
      "title": "空Latent图像(SD3)"
    }
  }
}
"""

def queue_prompt(prompt):
    p = {"prompt": prompt}
    data = json.dumps(p).encode('utf-8')
    req =  request.Request("http://127.0.0.1:9111/prompt", data=data)
    request.urlopen(req)


prompt = json.loads(prompt_text)
param_node =  {
        "inputs": {},
        "class_type": "BizyAir_PassParameter",
        "_meta": {
        "title": "☁️BizyAir PassParameter",
        "api_key": BIZYAIR_API_KEY,
        "prompt_id": "a-unique-prompt-id"
        }
    }
prompt["bizyair_magic_node"]=param_node
queue_prompt(prompt)

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

bizyengine-1.2.8.tar.gz (94.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

bizyengine-1.2.8-py3-none-any.whl (121.2 kB view details)

Uploaded Python 3

File details

Details for the file bizyengine-1.2.8.tar.gz.

File metadata

  • Download URL: bizyengine-1.2.8.tar.gz
  • Upload date:
  • Size: 94.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.13

File hashes

Hashes for bizyengine-1.2.8.tar.gz
Algorithm Hash digest
SHA256 4578b772eba5a1cea549c75636d311ebba0fef075a9c38bcca378931d23935f6
MD5 0c134d133d36dd5d56973fef2c405209
BLAKE2b-256 72fd67d63c4502d45977fc6ed9464933ce5e9e4d49fdc389491f445ee729e705

See more details on using hashes here.

File details

Details for the file bizyengine-1.2.8-py3-none-any.whl.

File metadata

  • Download URL: bizyengine-1.2.8-py3-none-any.whl
  • Upload date:
  • Size: 121.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.13

File hashes

Hashes for bizyengine-1.2.8-py3-none-any.whl
Algorithm Hash digest
SHA256 d43441fad771002e122e6997685ce77f7d6c623f59d3ffeac63639c02c7daeb0
MD5 36ba8079e5622ea3f28c622dcc097d4c
BLAKE2b-256 d9766cb17e9e4992976045ec44f474836bc1bade86398ed1afdc9eb739c5f43d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page