Platform For AI:Verify ComfyUI API integration

import requests
from eas_prediction import QueueClient

# Replace with your actual call information
input_url = "http://115************.cn-shanghai.pai-eas.aliyuncs.com/api/predict/ai4d_comfyuiapi_1u38************"
token = "Yjha************"
endpoint = "115************.cn-shanghai.pai-eas.aliyuncs.com"
service_name = "ai4d_comfyuiapi_1u38************/sink"

# Build the authenticated session
session = requests.session()
session.headers.update({"Authorization": f"{token}"})

# Workflow definition — a text-to-image pipeline with six nodes:
# Node 3 (KSampler): runs diffusion sampling with the specified seed and steps
# Node 4 (CheckpointLoaderSimple): loads the 3dAnimationDiffusion checkpoint
# Node 5 (EmptyLatentImage): creates a 512x512 blank latent canvas
# Node 6 (CLIPTextEncode): encodes the positive text prompt
# Node 7 (CLIPTextEncode): encodes the negative prompt ("text, watermark")
# Node 8 (VAEDecode): decodes the latent image to pixel space
# Node 9 (SaveImage): saves the output with the "ComfyUI" filename prefix
work_flow = {
    "3": {
        "inputs": {
            "seed": 156680208700286,
            "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": "K sampler"}
    },
    "4": {
        "inputs": {"ckpt_name": "3dAnimationDiffusion_v10.safetensors"},
        "class_type": "CheckpointLoaderSimple",
        "_meta": {"title": "Checkpoint loader (simple)"}
    },
    "5": {
        "inputs": {"width": 512, "height": 512, "batch_size": 1},
        "class_type": "EmptyLatentImage",
        "_meta": {"title": "Empty Latent"}
    },
    "6": {
        "inputs": {
            "text": "beautiful scenery nature glass bottle landscape, , purple galaxy bottle,",
            "clip": ["4", 1]
        },
        "class_type": "CLIPTextEncode",
        "_meta": {"title": "CLIP text encoder"}
    },
    "7": {
        "inputs": {"text": "text, watermark", "clip": ["4", 1]},
        "class_type": "CLIPTextEncode",
        "_meta": {"title": "CLIP text encoder"}
    },
    "8": {
        "inputs": {"samples": ["3", 0], "vae": ["4", 2]},
        "class_type": "VAEDecode",
        "_meta": {"title": "VAE decoding"}
    },
    "9": {
        "inputs": {"filename_prefix": "ComfyUI", "images": ["8", 0]},
        "class_type": "SaveImage",
        "_meta": {"title": "Save the image"}
    }
}

# Submit the task to the asynchronous queue
response = session.post(
    url=f'{input_url}/api_prompt?task_id=txt2img_test',
    json=work_flow
)
if response.status_code != 200:
    exit(f"send request error:{response.content}, response code:{response.status_code}")
else:
    print(f"send success, index is {response.content}")

# Poll the sink queue for the result
sink_queue = QueueClient(f'{endpoint}', f'{service_name}')
sink_queue.set_token(f'{token}')
sink_queue.init()

watcher = sink_queue.watch(0, 1, auto_commit=False)
for x in watcher.run():
    if 'task_id' in x.tags:
        print('index {} task_id is {}'.format(x.index, x.tags['task_id']))
        print(f'index {x.index} data is {x.data}')
        sink_queue.commit(x.index)

import requests

# Replace with your actual call information
url = "http://ai4d_comfyuiapi_1u38************.115************.cn-shanghai.pai-eas.aliyuncs.com/"
token = "Yjha************"

# Workflow definition — same six-node text-to-image pipeline:
# Node 3 (KSampler): runs diffusion sampling
# Node 4 (CheckpointLoaderSimple): loads the 3dAnimationDiffusion checkpoint
# Node 5 (EmptyLatentImage): creates a 512x512 blank latent canvas
# Node 6 (CLIPTextEncode): encodes the positive text prompt
# Node 7 (CLIPTextEncode): encodes the negative prompt
# Node 8 (VAEDecode): decodes the latent image to pixel space
# Node 9 (SaveImage): saves the output with the "ComfyUI" filename prefix
payload = {
    "prompt": {
        "3": {
            "inputs": {
                "seed": 156680208700286,
                "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": "K sampler"}
        },
        "4": {
            "inputs": {"ckpt_name": "3dAnimationDiffusion_v10.safetensors"},
            "class_type": "CheckpointLoaderSimple",
            "_meta": {"title": "Checkpoint loader (simple)"}
        },
        "5": {
            "inputs": {"width": 512, "height": 512, "batch_size": 1},
            "class_type": "EmptyLatentImage",
            "_meta": {"title": "Empty Latent"}
        },
        "6": {
            "inputs": {
                "text": "beautiful scenery nature glass bottle landscape, , purple galaxy bottle,",
                "clip": ["4", 1]
            },
            "class_type": "CLIPTextEncode",
            "_meta": {"title": "CLIP text encoder"}
        },
        "7": {
            "inputs": {"text": "text, watermark", "clip": ["4", 1]},
            "class_type": "CLIPTextEncode",
            "_meta": {"title": "CLIP text encoder"}
        },
        "8": {
            "inputs": {"samples": ["3", 0], "vae": ["4", 2]},
            "class_type": "VAEDecode",
            "_meta": {"title": "VAE decoding"}
        },
        "9": {
            "inputs": {"filename_prefix": "ComfyUI", "images": ["8", 0]},
            "class_type": "SaveImage",
            "_meta": {"title": "Save the image"}
        }
    }
}

# Submit the workflow — the service returns a prompt_id for tracking
session = requests.session()
session.headers.update({"Authorization": f"{token}"})
prompt_url = url + "prompt"

response = session.post(url=f'{prompt_url}', json=payload)
if response.status_code != 200:
    raise Exception(response.content)

data = response.json()
prompt_id = data['prompt_id']
print(f"get data: {data}, get prompt id: {prompt_id}")

# Retrieve results using the prompt_id
history_url = f"{url}history/{prompt_id}"

session = requests.session()
session.headers.update({"Authorization": f"{token}"})

response = session.get(url=f'{history_url}')
if response.status_code != 200:
    raise Exception(response.content)

data = response.json()
print(data)

# Parse the output to get image filenames
for prompt_id, prompt_data in data.items():
    outputs = prompt_data.get("outputs", {})
    for node_id, node_data in outputs.items():
        images = node_data.get("images", [])
        for image in images:
            filename = image.get("filename")
            print(f"Node number: {node_id}, Image filename: {filename}")