Z-Image-Turbo: 文生圖
高效的圖像產生基礎模型,採用單流擴散變換器,支援中英文。
下載工作流程在 Cloud 中試用 API 文件
Loading the grid…
Explore more grids
工作流程內部
來源範本的唯讀預覽。請在 Cloud 中開啟,以探索節點並進行變更。
Loading the graph
Open full-size workflow preview從您的程式碼呼叫此模型
以下請求使用與 Playground 相同的已準備節點圖和設定。每次提交都可能啟動付費執行;若提交結果不明,請勿自動重試提交。
1 取得 API 金鑰 ↗
What you need
- Runs on
- Comfy Cloud
- 金鑰
- COMFY_API_KEY
需要付費 Cloud 方案與點數。
下載 API JSONAPI 文件 ↗
# 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({
"9": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "z-image-turbo",
"images": [
"57:8",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"57:11": {
"class_type": "ModelSamplingAuraFlow",
"inputs": {
"model": [
"57:28",
0
],
"sampling": "flow",
"shift": 3
},
"_meta": {
"title": "ModelSamplingAuraFlow"
}
},
"57:13": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"batch_size": 1,
"height": 720,
"width": 1280
},
"_meta": {
"title": "EmptySD3LatentImage"
}
},
"57:27": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"57:30",
0
],
"text": "A wide-shot, eye-level photograph captures a lone Apollo astronaut standing beside a Lunar Roving Vehicle on the desolate moonscape. The astronaut’s white pressure suit, thick with wrinkled fabric folds, ribbed joints, and mechanical anodized connectors, glimmers under harsh, unfiltered sunlight. Subtle smudges of dark lunar dust cling to the knees and cuffs of the multi-layered garment. A gold-tinted reflective visor obscures their face, mirroring the stark, curved horizon and the bright specular highlight of the blazing sun, while a bulky white Portable Life Support System backpack, fitted with delicate telemetry sensors, is mounted to their rear. \n\nParked beside them, the metallic silver rover features distinctive red-orange fenders over wire-mesh wheels, which leave clear, geometric chevron tread patterns pressed deeply into the powdery, fine gray dust. An umbrella-shaped high-gain mesh antenna protrudes upward, surrounded by various clamped equipment bundles, scientific payload containers, and gold-foil-wrapped experiments strapped with utilitarian nylon ties. \n\nThe immediate ground is an intricately disturbed expanse of charcoal and light-gray regolith, heavily tracked with overlapping tread marks, boot prints showing ribbed sole patterns, and scattered with sharp, fragmented basalt rocks and mini-impact craters. In the far background, massive, softly rounded lunar mountains rise solemnly against an absolute, vacuum-black, starless sky. \n\nThe scene is side-lit from the low left, casting stark, ink-black, razor-sharp shadows across the undulating, cratered terrain that dramatically emphasize the intense contrast. The entire frame is marked by evenly spaced, small black Reseau crosshairs, a technical artifact of the historic medium-format Hasselblad 70mm camera. The palette is dominated by stark monochromatic grays, powdery whites, and obsidian shadows, punctuated solely by the mirrored gold visor, the vehicle's rust-colored accents, and delicate yellow thermal tape, all rendered with sharp, hyper-focused clarity and an infinite depth of field."
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"57:28": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "z_image_turbo_bf16.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"57:29": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "ae.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"57:3": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"57:13",
0
],
"model": [
"57:11",
0
],
"negative": [
"57:33",
0
],
"positive": [
"57:27",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 0,
"steps": 8
},
"_meta": {
"title": "KSampler"
}
},
"57:30": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen_3_4b.safetensors",
"device": "default",
"type": "lumina2"
},
"_meta": {
"title": "Load CLIP"
}
},
"57:33": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": [
"57:27",
0
]
},
"_meta": {
"title": "Conditioning Zero Out"
}
},
"57:8": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"57:3",
0
],
"vae": [
"57:29",
0
]
},
"_meta": {
"title": "VAE Decode"
}
}
})
# 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("9"):
output.to_file(output.name)試試範例
關於此工作流程
Z-Image-Turbo 文字轉圖像工作流程,能以 Z-Image-Turbo 模型高效地將文字描述轉為圖像。此流程採用單流擴散轉換器,支援中英文,適用於多元應用。流程核心為 f2fdebf6-dfaf-43b6-9eb2-7f70613cfdc1 節點,負責處理文字輸入並生成高品質圖像。SaveImage 節點用於儲存生成圖像,MarkdownNote 節點則提供流程說明與紀錄,方便理解與追蹤。
技術上,流程充分發揮 Z-Image-Turbo 模型的高效能,針對速度與品質最佳化。模型採用擴散過程,從雜訊逐步細化為符合輸入文字的圖像。此方法不僅確保高品質輸出,也比傳統方法更快。多語言支援讓此流程適用於全球應用,是多語言內容創作的理想工具。
問答
Z-Image-Turbo 模型支援中英文,可靈活進行多語言文字轉圖像生成。
模型會從雜訊逐步細化為清晰圖像,透過多次轉換確保高品質且高效率的輸出。
可以,只要遵守 Z-Image-Turbo 模型的授權條款,即可用於商業專案。
可依作者說明中的 GitHub 問題回報連結回報問題。
相關工作流程
- ZZ-Image-Turbo
1.1 入門-文字轉圖像
- ZZ-Image-Turbo
2.1 Creator-擴散基礎
- ZZ-Image-Turbo
2.2 Creator - 擴散引導
- ZZ-Image-Turbo
2.3 Creator:影像放大與分析
- Wan2.2, Z-Image-Turbo
AIrt MAchIne
- Google Gemini, Kling 3.0, Z-Image-Turbo
AIrt MAchIne(API 版本)
- ZZ-Image-Turbo
Z-Image-Turbo 控制生圖
- ZZ-Image-Turbo
Z-Image-Turbo_Oldschool-Hud-Graphics
- ZZ-Image-Turbo
切換節點
- ZZ-Image-Turbo
圖像放大:Z-Image-Turbo 2K
- Kling 2.6, Nano Banana Pro, Z-Image-Turbo
圖生影片
- ZZ-Image-Turbo
從列表批次處理文字提示