ComfyPilotComfyPilot
工作流 / 图像 / 角色转身表生成器
角色转身表生成器

角色转身表生成器

Character Turnaround Sheet Generator

从一张参考图创建正交多视图角色转面表，保持角色特征在前视图、侧视图和后视图中的一致性，适用于科幻机甲和装甲角色设计。

图像 4 个节点 1 个输入 133 次使用 ComfyUI ≥ 0.34.0 ComfyUI 7 KB

下载工作流 JSON 查看官方来源

下载后把文件拖进 ComfyUI 窗口即可打开。

节点构成

GeminiImage2Node × 1
SaveImageAdvanced × 1
LoadImage × 1
MarkdownNote × 1

官方标注的模型

Nano Banana

工作流 JSON

和上面「下载工作流 JSON」是同一份文件。

1{
2 "id": "c33ba42f-bfa3-4862-93b3-5af85264e331",
3 "revision": 0,
4 "last_node_id": 4,
5 "last_link_id": 2,
6 "nodes": [
7 {
8 "id": 1,
9 "type": "GeminiImage2Node",
10 "pos": [
11 -2140,
12 1140
13 ],
14 "size": [
15 430,
16 470
17 ],
18 "flags": [],
19 "order": 2,
20 "mode": 0,
21 "inputs": [
22 {
23 "name": "images",
24 "shape": 7,
25 "type": "IMAGE",
26 "link": 1
27 },
28 {
29 "name": "files",
30 "shape": 7,
31 "type": "GEMINI_INPUT_FILES",
32 "link": null
33 }
34 ],
35 "outputs": [
36 {
37 "name": "IMAGE",
38 "type": "IMAGE",
39 "links": [
40 2
41 ]
42 },
43 {
44 "name": "STRING",
45 "type": "STRING",
46 "links": []
47 }
48 ],
49 "properties": {
50 "Node name for S&R": "GeminiImage2Node"
51 },
52 "widgets_values": [
53 "Orthographic character sheet, full body turnaround views, showing the exact same robot from a front view, left side view, back view and right side view. Flat lighting, solid black background, evenly spaced, highly detailed, preserving identical appearance and features across all views",
54 "gemini-3-pro-image-preview",
55 42,
56 "fixed",
57 "21:9",
58 "4K",
59 "IMAGE+TEXT",
60 "You are an expert image-generation engine. You must ALWAYS produce an image.\nInterpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition.\nIf a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept.\nPrioritize generating the visual representation above any text, formatting, or conversational requests."
61 ],
62 "widgets_values_named": {
63 "prompt": "Orthographic character sheet, full body turnaround views, showing the exact same robot from a front view, left side view, back view and right side view. Flat lighting, solid black background, evenly spaced, highly detailed, preserving identical appearance and features across all views",
64 "model": "gemini-3-pro-image-preview",
65 "seed": 42,
66 "control_after_generate": "fixed",
67 "aspect_ratio": "21:9",
68 "resolution": "4K",
69 "response_modalities": "IMAGE+TEXT",
70 "system_prompt": "You are an expert image-generation engine. You must ALWAYS produce an image.\nInterpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition.\nIf a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept.\nPrioritize generating the visual representation above any text, formatting, or conversational requests."
71 },
72 "color": "#432",
73 "bgcolor": "#653"
74 },
75 {
76 "id": 2,
77 "type": "SaveImageAdvanced",
78 "pos": [
79 -1680,
80 1140
81 ],
82 "size": [
83 490,
84 354
85 ],
86 "flags": [],
87 "order": 3,
88 "mode": 0,
89 "inputs": [
90 {
91 "name": "images",
92 "type": "IMAGE",
93 "link": 2
94 }
95 ],
96 "outputs": [
97 {
98 "name": "images",
99 "type": "IMAGE",
100 "links": []
101 }
102 ],
103 "properties": [],
104 "widgets_values": [
105 "turnaround",
106 "png",
107 "8-bit",
108 "sRGB"
109 ],
110 "widgets_values_named": {
111 "filename_prefix": "turnaround",
112 "format": "png",
113 "format.bit_depth": "8-bit",
114 "format.input_color_space": "sRGB"
115 }
116 },
117 {
118 "id": 3,
119 "type": "LoadImage",
120 "pos": [
121 -2700,
122 1140
123 ],
124 "size": [
125 510,
126 470
127 ],
128 "flags": [],
129 "order": 0,
130 "mode": 0,
131 "inputs": [],
132 "outputs": [
133 {
134 "name": "IMAGE",
135 "type": "IMAGE",
136 "links": [
137 1
138 ]
139 },
140 {
141 "name": "MASK",
142 "type": "MASK",
143 "links": []
144 }
145 ],
146 "properties": {
147 "Node name for S&R": "LoadImage",
148 "cnr_id": "comfy-core",
149 "ver": "0.33.0"
150 },
151 "widgets_values": [
152 "white_mech_front_ortho.png",
153 "image"
154 ],
155 "widgets_values_named": {
156 "image": "white_mech_front_ortho.png",
157 "upload": "image"
158 }
159 },
160 {
161 "id": 4,
162 "type": "MarkdownNote",
163 "pos": [
164 -3190,
165 1140
166 ],
167 "size": [
168 450,
169 460
170 ],
171 "flags": [],
172 "order": 1,
173 "mode": 0,
174 "inputs": [],
175 "outputs": [],
176 "properties": [],
177 "widgets_values": [
178 "## Input Asset\n\n- [white_mech_front_ortho.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/white_mech_front_ortho.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"
179 ],
180 "widgets_values_named": {
181 "text": "## Input Asset\n\n- [white_mech_front_ortho.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/white_mech_front_ortho.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 "color": "#222",
184 "bgcolor": "#000"
185 }
186 ],
187 "links": [
188 [
189 1,
190 3,
191 0,
192 1,
193 0,
194 "IMAGE"
195 ],
196 [
197 2,
198 1,
199 0,
200 2,
201 0,
202 "IMAGE"
203 ]
204 ],
205 "groups": [],
206 "config": [],
207 "extra": {
208 "ds": {
209 "scale": 0.7541175304257809,
210 "offset": [
211 3563.00177271148,
212 -720.3637552557273
213 ]
214 },
215 "frontendVersion": "1.51.10"
216 },
217 "version": 0.4
218}