另外，小編也找到了一套相當實用的 Z-Image-Turbo 資源，讓大家能夠在 ComfyUI 中快速體驗高品質的文生圖功能。
Z-Image-Turbo 主要需要下載以下三個模型：
- z_image_turbo_bf16.safetensors［下載］
- ae.safetensors［下載］
- qwen_3_4b.safetensors［下載］
下載完成後，請依照模型類型分別放置到對應目錄：
ComfyUI\models\diffusion_models\
└─ z_image_turbo_bf16.safetensors
ComfyUI\models\vae\
└─ ae.safetensors
ComfyUI\models\text_encoders\
└─ qwen_3_4b.safetensors
完成模型部署後，重新啟動 ComfyUI，接著載入下方提供的 Workflow JSON 檔案。
{
"id": "d45a6fab-47b7-4ecf-94ec-600dfd20b7f9",
"revision": 0,
"last_node_id": 56,
"last_link_id": 62,
"nodes": [
{
"id": 46,
"type": "UNETLoader",
"pos": [
110,
313
],
"size": [
270,
82
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
62
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "UNETLoader",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"z_image_turbo_bf16.safetensors",
"default"
]
},
{
"id": 47,
"type": "ModelSamplingAuraFlow",
"pos": [
902,
267
],
"size": [
270,
58
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 62
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
40
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "ModelSamplingAuraFlow",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
3
]
},
{
"id": 39,
"type": "CLIPLoader",
"pos": [
110,
438
],
"size": [
270,
106
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
44
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "CLIPLoader",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"qwen_3_4b.safetensors",
"lumina2",
"default"
]
},
{
"id": 42,
"type": "ConditioningZeroOut",
"pos": [
658,
728
],
"size": [
204.134765625,
26
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 36
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
42
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "ConditioningZeroOut",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": []
},
{
"id": 44,
"type": "KSampler",
"pos": [
900,
375
],
"size": [
270,
262
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 40
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 41
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 42
},
{
"name": "latent_image",
"type": "LATENT",
"link": 43
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
38
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "KSampler",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
479070766613392,
"randomize",
9,
1,
"res_multistep",
"simple",
1
]
},
{
"id": 40,
"type": "VAELoader",
"pos": [
110,
583
],
"size": [
270,
58
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
39
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "VAELoader",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"ae.safetensors"
]
},
{
"id": 43,
"type": "VAEDecode",
"pos": [
1247,
172
],
"size": [
140,
46
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 38
},
{
"name": "vae",
"type": "VAE",
"link": 39
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
45
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "VAEDecode",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": []
},
{
"id": 9,
"type": "SaveImage",
"pos": [
1240,
260
],
"size": [
270,
270
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 45
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "SaveImage",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"Z-Image/ComfyUI"
]
},
{
"id": 45,
"type": "CLIPTextEncode",
"pos": [
448,
313
],
"size": [
400,
200
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 44
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
36,
41
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "CLIPTextEncode",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"A professional female cosplay model dressed in a blue and pink futuristic combat suit with white armor details and a pink cat-ear gaming headset. The design resembles a high-end Korean esports pilot uniform with a cute rabbit emblem on the chest.\n\nShe has long dark hair, soft bangs, large expressive eyes, natural makeup, glossy lips, and smooth realistic skin. Her expression is friendly and charming.\n\nThe portrait is photographed from a slightly elevated angle, emphasizing eye contact and creating an intimate connection with the viewer.\n\nSoft studio lighting, beauty dish lighting, premium cosplay photography, realistic skin texture, subtle bokeh background, shallow depth of field, high-end fashion photography, photorealistic, detailed costume materials, realistic leather and armor textures, cinematic quality.\n"
]
},
{
"id": 41,
"type": "EmptySD3LatentImage",
"pos": [
114,
741
],
"size": [
270,
106
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
43
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.21.1",
"Node name for S&R": "EmptySD3LatentImage",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.8",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
832,
1472,
1
]
}
],
"links": [
[
62,
46,
0,
47,
0,
"MODEL"
],
[
40,
47,
0,
44,
0,
"MODEL"
],
[
44,
39,
0,
45,
0,
"CLIP"
],
[
36,
45,
0,
42,
0,
"CONDITIONING"
],
[
41,
45,
0,
44,
1,
"CONDITIONING"
],
[
42,
42,
0,
44,
2,
"CONDITIONING"
],
[
43,
41,
0,
44,
3,
"LATENT"
],
[
38,
44,
0,
43,
0,
"LATENT"
],
[
39,
40,
0,
43,
1,
"VAE"
],
[
45,
43,
0,
9,
0,
"IMAGE"
]
],
"groups": [],
"config": {},
"extra": {
"ue_links": [],
"ds": {
"scale": 1.0013793103448276,
"offset": [
-9.134814049586794,
-18.527777777777885
]
},
"links_added_by_ue": [],
"frontendVersion": "1.43.18",
"VHS_latentpreview": false,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"version": 0.4
}
設定完成後，即可透過 Z-Image-Turbo 輸入提示詞（Prompt），快速生成高品質且符合需求的 AI 圖像。相較於傳統工作流，Z-Image-Turbo 擁有更簡潔的設定流程，非常適合作為入門體驗或日常快速生成圖片的工具。
