工作流 /
图像 /
GPT图像2.5 Flare：图像编辑
GPT图像2.5 Flare：图像编辑
GPT Image 2.5 Flare: Image Edit
图像重做与局部修改模板。保持场景、姿态、光照和构图不变，仅编辑服装、发型或局部详情。由GPT-Image-2.5-Flare驱动的快速预览和迭代风格调整。
图像
4 个节点 1 个输入 811 次使用 ComfyUI ≥ 0.35.0 ComfyUI 6 KB
节点构成
LoadImage
× 1
SaveImageAdvanced
× 1
OpenAIGPTImageNodeV2
× 1
MarkdownNote
× 1
官方标注的模型
GPT Image 2.5
工作流 JSON
和上面「下载工作流 JSON」是同一份文件。
1{
2 "id": "7a06a6de-067d-4d41-b7bf-7d6add20ec8c",
3 "revision": 0,
4 "last_node_id": 375,
5 "last_link_id": 555,
6 "nodes": [
7 {
8 "id": 360,
9 "type": "LoadImage",
10 "pos": [
11 -1310,
12 7010
13 ],
14 "size": [
15 390,
16 450
17 ],
18 "flags": [],
19 "order": 0,
20 "mode": 0,
21 "inputs": [],
22 "outputs": [
23 {
24 "name": "IMAGE",
25 "type": "IMAGE",
26 "links": [
27 554
28 ]
29 },
30 {
31 "name": "MASK",
32 "type": "MASK",
33 "links": null
34 }
35 ],
36 "properties": {
37 "Node name for S&R": "LoadImage"
38 },
39 "widgets_values": [
40 "outfit_swap_base_gpt_image25.png",
41 "image"
42 ],
43 "widgets_values_named": {
44 "image": "outfit_swap_base_gpt_image25.png",
45 "upload": "image"
46 }
47 },
48 {
49 "id": 373,
50 "type": "SaveImageAdvanced",
51 "pos": [
52 -424,
53 7010
54 ],
55 "size": [
56 520,
57 378
58 ],
59 "flags": [],
60 "order": 3,
61 "mode": 0,
62 "inputs": [
63 {
64 "name": "images",
65 "type": "IMAGE",
66 "link": 553
67 }
68 ],
69 "outputs": [
70 {
71 "name": "images",
72 "type": "IMAGE",
73 "links": null
74 }
75 ],
76 "properties": [],
77 "widgets_values": [
78 "GPT_image_2.5_flare_image_edit",
79 "png",
80 "8-bit",
81 "sRGB"
82 ],
83 "widgets_values_named": {
84 "filename_prefix": "GPT_image_2.5_flare_image_edit",
85 "format": "png",
86 "format.bit_depth": "8-bit",
87 "format.input_color_space": "sRGB"
88 }
89 },
90 {
91 "id": 374,
92 "type": "OpenAIGPTImageNodeV2",
93 "pos": [
94 -872,
95 7010
96 ],
97 "size": [
98 400,
99 454
100 ],
101 "flags": [],
102 "order": 2,
103 "mode": 0,
104 "inputs": [
105 {
106 "name": "model.images.image_1",
107 "shape": 7,
108 "type": "IMAGE",
109 "link": 554
110 },
111 {
112 "name": "model.images.image_2",
113 "shape": 7,
114 "type": "IMAGE",
115 "link": null
116 },
117 {
118 "name": "model.mask",
119 "shape": 7,
120 "type": "MASK",
121 "link": null
122 }
123 ],
124 "outputs": [
125 {
126 "name": "IMAGE",
127 "type": "IMAGE",
128 "links": [
129 553
130 ]
131 }
132 ],
133 "properties": {
134 "Node name for S&R": "OpenAIGPTImageNodeV2"
135 },
136 "widgets_values": [
137 "Keep the background environment, concrete walls, blue sky, sunlight, shadows, camera angle, framing and composition completely unchanged. Change her into a soft floral tulle dress, and style her hair into loose bohemian curls with small flowers.\n",
138 "gpt-image-2.5-flare",
139 "auto",
140 1024,
141 1024,
142 "auto",
143 "low",
144 1,
145 183495656,
146 "randomize"
147 ],
148 "widgets_values_named": {
149 "prompt": "Keep the background environment, concrete walls, blue sky, sunlight, shadows, camera angle, framing and composition completely unchanged. Change her into a soft floral tulle dress, and style her hair into loose bohemian curls with small flowers.\n",
150 "model": "gpt-image-2.5-flare",
151 "model.size": "auto",
152 "model.custom_width": 1024,
153 "model.custom_height": 1024,
154 "model.background": "auto",
155 "model.quality": "low",
156 "n": 1,
157 "seed": 183495656,
158 "control_after_generate": "randomize"
159 },
160 "color": "#432",
161 "bgcolor": "#653"
162 },
163 {
164 "id": 375,
165 "type": "MarkdownNote",
166 "pos": [
167 -1720,
168 7010
169 ],
170 "size": [
171 360,
172 360
173 ],
174 "flags": [],
175 "order": 1,
176 "mode": 0,
177 "inputs": [],
178 "outputs": [],
179 "properties": [],
180 "widgets_values": [
181 "## Input Asset\n\n- [outfit_swap_base_gpt_image25.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/outfit_swap_base_gpt_image25.png)\n\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
182 ],
183 "widgets_values_named": {
184 "text": "## Input Asset\n\n- [outfit_swap_base_gpt_image25.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/outfit_swap_base_gpt_image25.png)\n\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
185 },
186 "color": "#222",
187 "bgcolor": "#000"
188 }
189 ],
190 "links": [
191 [
192 553,
193 374,
194 0,
195 373,
196 0,
197 "IMAGE"
198 ],
199 [
200 554,
201 360,
202 0,
203 374,
204 0,
205 "IMAGE"
206 ]
207 ],
208 "groups": [],
209 "config": [],
210 "extra": {
211 "ds": {
212 "scale": 0.9135381560640724,
213 "offset": [
214 1958.7521026091772,
215 -6604.062160531607
216 ]
217 },
218 "frontendVersion": "1.51.10",
219 "VHS_latentpreview": false,
220 "VHS_latentpreviewrate": 0,
221 "VHS_MetadataImage": true,
222 "VHS_KeepIntermediate": true
223 },
224 "version": 0.4
225}