Mage-Flow
Generate images with Mage-Flow, and compare every CFG, steps, sampler and scheduler on one prompt.
Baixar workflowExperimentar no Cloud Documentação da API
Loading the grid…
Explore more grids
Your output will appear here.
Dentro do workflow
Uma prévia somente leitura do modelo de origem. Abra-o no Cloud para explorar os nós e fazer alterações.
Loading the graph
Open full-size workflow previewArquivos neste workflow
- Comfy Cloud
- Sim
- Saída
- Imagem
- Autor
- Autor indisponível
Chame este modelo pelo seu código
A solicitação abaixo usa o mesmo grafo e as mesmas configurações preparadas no Playground. Cada envio pode iniciar uma execução paga; não tente novamente automaticamente um envio cujo resultado seja desconhecido.
1 Obter chave de API ↗
What you need
- Runs on
- Comfy Cloud
- Chave
- COMFY_API_KEY
Requer um plano pago do Cloud e créditos.
Baixar JSON da APIDocumentação da API ↗
# Python 3.10+: pip install comfy-sdk==0.4.0
import os
from comfy_sdk import Comfy
api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
"1": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "mage_flow_int8_convrot.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"2": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen3vl_4b_bf16.safetensors",
"device": "default",
"type": "mage"
},
"_meta": {
"title": "Load CLIP"
}
},
"3": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "mage_flow_vae_bf16.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"6": {
"class_type": "TextEncodeMageFlowEdit",
"inputs": {
"batch_size": 1,
"clip": [
"2",
0
],
"height": 768,
"negative_prompt": "",
"prompt": "Epic wide landscape photograph of arctic tundra in peak autumn color: a vast valley carpeted in crimson, orange and gold dwarf shrubs, a braided glacial river with silver channels winding to rugged mountains dusted with the first snow, low dramatic clouds with breaks of soft sunlight, immense scale, ultra-detailed, large format landscape photography, no people, no text.",
"vae": [
"3",
0
],
"width": 1344
},
"_meta": {
"title": "TextEncodeMageFlowEdit"
}
},
"90": {
"class_type": "PrimitiveFloat",
"inputs": {
"value": 5
},
"_meta": {
"title": "CFG (sweep)"
}
},
"91": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 30
},
"_meta": {
"title": "Steps (sweep)"
}
},
"92": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
},
"_meta": {
"title": "Sampler (sweep)"
}
},
"93": {
"class_type": "CFGGuider",
"inputs": {
"cfg": [
"90",
0
],
"model": [
"1",
0
],
"negative": [
"6",
1
],
"positive": [
"6",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"94": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 42
},
"_meta": {
"title": "Noise (seed 42)"
}
},
"100": {
"class_type": "BasicScheduler",
"inputs": {
"denoise": 1,
"model": [
"1",
0
],
"scheduler": "simple",
"steps": [
"91",
0
]
},
"_meta": {
"title": "Scheduler simple"
}
},
"200": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"93",
0
],
"latent_image": [
"6",
2
],
"noise": [
"94",
0
],
"sampler": [
"92",
0
],
"sigmas": [
"100",
0
]
},
"_meta": {
"title": "Sample simple"
}
},
"400": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"200",
0
],
"vae": [
"3",
0
]
},
"_meta": {
"title": "Decode simple"
}
},
"599": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "mageflow_strip",
"images": [
"400",
0
]
},
"_meta": {
"title": "Save Image"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)
for output in job.get_outputs("599"):
output.to_file(output.name)