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-1.2.10.tar.gz (94.8 kB view details)

Uploaded Source

Built Distribution

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

bizyengine-1.2.10-py3-none-any.whl (122.1 kB view details)

Uploaded Python 3

File details

Details for the file bizyengine-1.2.10.tar.gz.

File metadata

  • Download URL: bizyengine-1.2.10.tar.gz
  • Upload date:
  • Size: 94.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for bizyengine-1.2.10.tar.gz
Algorithm Hash digest
SHA256 6e33537697b1156ed8723f85f09933d98b802ebcd0e11df9ec341f04646aecaf
MD5 d3f7d3d7860f5366e8269d5662ba2890
BLAKE2b-256 3762494f0bb934a5b3c61e2b814e808d69e128aaf250589bddb3d7163549ef7a

See more details on using hashes here.

File details

Details for the file bizyengine-1.2.10-py3-none-any.whl.

File metadata

  • Download URL: bizyengine-1.2.10-py3-none-any.whl
  • Upload date:
  • Size: 122.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for bizyengine-1.2.10-py3-none-any.whl
Algorithm Hash digest
SHA256 86ee73eb28587b45d41875fd142263cd8e672354e7e51b7d3219c212b28f904e
MD5 a003114d27d77cda9d1bd851b326d5ce
BLAKE2b-256 8164c19451530cf2bd8c76096c273102ec43db9cb56f648ea3d599d2176d2f2b

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