Spaces:
Running on Zero
Running on Zero
Examples: keep the 8 most striking (adds the promo's character style file); drop the dense-layout claim (part 2)
Browse files- .gitattributes +1 -0
- compare.py +2 -2
- examples/manifest.json +49 -94
- examples/t2i_style_file.png +3 -0
.gitattributes
CHANGED
|
@@ -196,3 +196,4 @@ examples/qwen_poster.png filter=lfs diff=lfs merge=lfs -text
|
|
| 196 |
examples/qwen_rgba_bride.png filter=lfs diff=lfs merge=lfs -text
|
| 197 |
examples/qwen_storyboard.png filter=lfs diff=lfs merge=lfs -text
|
| 198 |
examples/qwen_storyboard_in1.webp filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 196 |
examples/qwen_rgba_bride.png filter=lfs diff=lfs merge=lfs -text
|
| 197 |
examples/qwen_storyboard.png filter=lfs diff=lfs merge=lfs -text
|
| 198 |
examples/qwen_storyboard_in1.webp filter=lfs diff=lfs merge=lfs -text
|
| 199 |
+
examples/t2i_style_file.png filter=lfs diff=lfs merge=lfs -text
|
compare.py
CHANGED
|
@@ -69,8 +69,8 @@ def render():
|
|
| 69 |
f"**viggle-turbo (6 steps) vs Qwen-Image-2.1 (40 steps)** on {len(CASES)} of the 37 examples of the official "
|
| 70 |
"[Qwen/Qwen-Image-2.1 Space](https://huggingface.co/spaces/Qwen/Qwen-Image-2.1). Both models get the same prompt, "
|
| 71 |
"input images and seed, with prompt enhancement off, one sample each and no seed picking. "
|
| 72 |
-
f"At **{speedup:.1f}× less time** the turbo is very competitive with the base model
|
| 73 |
-
"
|
| 74 |
"Pick an example on the left, then drag the slider. The 5 dense-text examples open on the 8-step turbo (6 steps is in "
|
| 75 |
"the menu), and the menus also offer Qwen's own API reference where the Space ships one.\n\n"
|
| 76 |
f"Median time, editing: **{median(edits, 'turbo_s'):.1f} s vs {median(edits, 'base_s'):.1f} s** · "
|
|
|
|
| 69 |
f"**viggle-turbo (6 steps) vs Qwen-Image-2.1 (40 steps)** on {len(CASES)} of the 37 examples of the official "
|
| 70 |
"[Qwen/Qwen-Image-2.1 Space](https://huggingface.co/spaces/Qwen/Qwen-Image-2.1). Both models get the same prompt, "
|
| 71 |
"input images and seed, with prompt enhancement off, one sample each and no seed picking. "
|
| 72 |
+
f"At **{speedup:.1f}× less time** the turbo is very competitive with the base model; the clearest gaps are "
|
| 73 |
+
"small, dense text (8 steps narrows it) and complicated edits, where the base is still ahead. "
|
| 74 |
"Pick an example on the left, then drag the slider. The 5 dense-text examples open on the 8-step turbo (6 steps is in "
|
| 75 |
"the menu), and the menus also offer Qwen's own API reference where the Space ships one.\n\n"
|
| 76 |
f"Median time, editing: **{median(edits, 'turbo_s'):.1f} s vs {median(edits, 'base_s'):.1f} s** · "
|
examples/manifest.json
CHANGED
|
@@ -1,49 +1,4 @@
|
|
| 1 |
[
|
| 2 |
-
{
|
| 3 |
-
"prompt": "The person from image 1 is petting the cat from image 2, the bird from image 3 is next to them",
|
| 4 |
-
"refs": [
|
| 5 |
-
"woman1.webp",
|
| 6 |
-
"cat_window.webp",
|
| 7 |
-
"bird.webp"
|
| 8 |
-
],
|
| 9 |
-
"result": "edit_3ref_klein.png",
|
| 10 |
-
"info": "Pre-rendered example · seed `42` · 928×1152 · 6 steps · v0.2.1 LoRA r256 · prompt enhanced",
|
| 11 |
-
"used_prompt": "Compose a scene where the person from <image1>, standing beside the vintage brown car, is gently petting the fluffy cat from <image2> that is perched on a stone windowsill with green shutters, while the bird from <image3>, with a red crown and long beak, stands next to them, all under warm cinematic lighting with a shallow depth of field focusing on the trio, keeping the background and subjects' identities from the input images unchanged.",
|
| 12 |
-
"steps": 6,
|
| 13 |
-
"size_label": "Auto · match the last reference (1024² area)",
|
| 14 |
-
"enhance": true,
|
| 15 |
-
"seed": 42
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"prompt": "Create a premium, minimalist launch graphic for an AI image model, designed for a Twitter/X announcement.\n\nAspect ratio: 16:9.\nStyle: elegant, high-end, modern AI product launch visual. Clean Apple / NVIDIA / premium creative-software aesthetic. Dark, cinematic, sophisticated, not flashy or cluttered.\n\nBACKGROUND\n- Deep black to charcoal gradient background.\n- Very subtle blue and violet ambient glow.\n- Soft cinematic lighting, slight glossy reflections near the bottom.\n- Large areas of negative space.\n- No unnecessary particles, grids, icons, decorative UI, or busy textures.\n\nTOP-LEFT TYPOGRAPHY\n\nMain title:\n“Qwen-Image-2.1 ❤️ Viggle Turbo”\n\n- Large bold geometric sans-serif.\n- Clean Swiss-style typography.\n- Bright soft-white text.\n- Red heart between the two model names.\n- Precise kerning and professional spacing.\n- Keep the title on one line.\n- Position around 4–5% from the left and 8–10% from the top.\n\nDirectly underneath, smaller subtitle:\n“DMD-distilled · Generate & Edit”\n\n- Thin or regular sans-serif.\n- Around 30–35% of the main title font size.\n- Soft light-gray / off-white.\n- Generous letter spacing.\n- Minimal and understated.\n\nCENTER HERO MESSAGE\n\nLarge dominant typography:\n\n“6-step”\n“generation”\n\non two lines.\n\n- “6-step” should be extremely large.\n- “generation” slightly smaller but still bold.\n- Heavy geometric sans-serif.\n- White / very subtle cool-white gradient.\n- Tight line spacing.\n- Perfectly clean typography.\n- Position slightly above the vertical center.\n- The text should be the strongest visual element in the design.\n- No exaggerated 3D text, extrusion, chrome effects, or heavy shadows.\n- Only a very subtle soft glow.\n\nVISUAL ELEMENT\n\nCreate a single elegant curved ribbon of generated images flowing across the lower half of the composition.\n\nThe ribbon should:\n- Start from the lower-left foreground.\n- Curve smoothly toward the center-right.\n- Continue upward toward the upper-right background.\n- Feel like a sophisticated cinematic film strip or flowing image-generation sequence.\n- Use approximately 5–7 image panels only.\n- Avoid a dense collage.\n\nEach panel:\n- Rounded rectangle.\n- Thin subtle border.\n- Premium glossy display appearance.\n- Slight perspective distortion following the curve.\n- Gradually decrease in size toward the background.\n- Use realistic generated landscape photography:\n • alpine lake\n • mountain valley\n • waterfall\n • dramatic mountain peaks\n • coastal sunset\n- Rich but natural colors.\n- Foreground panels sharp, distant panels progressively softer / slightly blurred.\n- Strong depth-of-field.\n\nThe ribbon itself should have an extremely subtle luminous edge:\n- cyan / electric blue on the left\n- transitioning gently toward violet / magenta on the right\n\nKeep the glow restrained and premium.\nDo not make it look like cyberpunk neon.\n\nLIGHTING\n\nAdd one very thin horizontal blue-to-violet light flare passing subtly behind the “6-step” text.\n\nUse soft reflected blue/violet light underneath the image ribbon.\n\nLighting should feel cinematic and expensive, not game-like.\n\nBOTTOM-RIGHT\n\nSmall footer:\n“Generate with viggle-turbo”\n\n- Small clean sans-serif.\n- White / light gray.\n- Bottom-right aligned.\n- Approximately 5% from the right and 6–8% from the bottom.\n- Lots of breathing room.\n- Do not make it prominent.\n\nOVERALL COMPOSITION\n\nThe visual hierarchy should clearly be:\n\n1. “6-step generation”\n2. “Qwen-Image-2.1 ❤️ Viggle Turbo”\n3. flowing generated-image ribbon\n4. “DMD-distilled · Generate & Edit”\n5. small “Generate with viggle-turbo.” footer\n\nThe graphic should immediately communicate:\nfast generation, image generation, premium AI model, six-step inference.\n\nOverall aesthetic:\nminimal, elegant, expensive, technically sophisticated, cinematic, polished, restrained, premium AI launch campaign.\n\nAvoid:\n- excessive neon\n- cyberpunk look\n- too many thumbnails\n- busy collage layouts\n- random icons\n- fake UI elements\n- gradients inside every object\n- excessive lens flares\n- heavy shadows\n- 3D metallic typography\n- cartoon imagery\n- excessive text\n- logos other than the specified text\n- watermark\n- spelling errors\n- distorted letters\n- duplicated text",
|
| 19 |
-
"refs": [
|
| 20 |
-
null,
|
| 21 |
-
null,
|
| 22 |
-
null
|
| 23 |
-
],
|
| 24 |
-
"result": "t2i_launch.png",
|
| 25 |
-
"info": "Pre-rendered example · seed `3` · 2496×1664 · 8 steps · v0.2.1 LoRA r256 · prompt sent as written (enhancement off)",
|
| 26 |
-
"used_prompt": "Create a premium, minimalist launch graphic for an AI image model, designed for a Twitter/X announcement.\n\nAspect ratio: 16:9.\nStyle: elegant, high-end, modern AI product launch visual. Clean Apple / NVIDIA / premium creative-software aesthetic. Dark, cinematic, sophisticated, not flashy or cluttered.\n\nBACKGROUND\n- Deep black to charcoal gradient background.\n- Very subtle blue and violet ambient glow.\n- Soft cinematic lighting, slight glossy reflections near the bottom.\n- Large areas of negative space.\n- No unnecessary particles, grids, icons, decorative UI, or busy textures.\n\nTOP-LEFT TYPOGRAPHY\n\nMain title:\n“Qwen-Image-2.1 ❤️ Viggle Turbo”\n\n- Large bold geometric sans-serif.\n- Clean Swiss-style typography.\n- Bright soft-white text.\n- Red heart between the two model names.\n- Precise kerning and professional spacing.\n- Keep the title on one line.\n- Position around 4–5% from the left and 8–10% from the top.\n\nDirectly underneath, smaller subtitle:\n“DMD-distilled · Generate & Edit”\n\n- Thin or regular sans-serif.\n- Around 30–35% of the main title font size.\n- Soft light-gray / off-white.\n- Generous letter spacing.\n- Minimal and understated.\n\nCENTER HERO MESSAGE\n\nLarge dominant typography:\n\n“6-step”\n“generation”\n\non two lines.\n\n- “6-step” should be extremely large.\n- “generation” slightly smaller but still bold.\n- Heavy geometric sans-serif.\n- White / very subtle cool-white gradient.\n- Tight line spacing.\n- Perfectly clean typography.\n- Position slightly above the vertical center.\n- The text should be the strongest visual element in the design.\n- No exaggerated 3D text, extrusion, chrome effects, or heavy shadows.\n- Only a very subtle soft glow.\n\nVISUAL ELEMENT\n\nCreate a single elegant curved ribbon of generated images flowing across the lower half of the composition.\n\nThe ribbon should:\n- Start from the lower-left foreground.\n- Curve smoothly toward the center-right.\n- Continue upward toward the upper-right background.\n- Feel like a sophisticated cinematic film strip or flowing image-generation sequence.\n- Use approximately 5–7 image panels only.\n- Avoid a dense collage.\n\nEach panel:\n- Rounded rectangle.\n- Thin subtle border.\n- Premium glossy display appearance.\n- Slight perspective distortion following the curve.\n- Gradually decrease in size toward the background.\n- Use realistic generated landscape photography:\n • alpine lake\n • mountain valley\n • waterfall\n • dramatic mountain peaks\n • coastal sunset\n- Rich but natural colors.\n- Foreground panels sharp, distant panels progressively softer / slightly blurred.\n- Strong depth-of-field.\n\nThe ribbon itself should have an extremely subtle luminous edge:\n- cyan / electric blue on the left\n- transitioning gently toward violet / magenta on the right\n\nKeep the glow restrained and premium.\nDo not make it look like cyberpunk neon.\n\nLIGHTING\n\nAdd one very thin horizontal blue-to-violet light flare passing subtly behind the “6-step” text.\n\nUse soft reflected blue/violet light underneath the image ribbon.\n\nLighting should feel cinematic and expensive, not game-like.\n\nBOTTOM-RIGHT\n\nSmall footer:\n“Generate with viggle-turbo”\n\n- Small clean sans-serif.\n- White / light gray.\n- Bottom-right aligned.\n- Approximately 5% from the right and 6–8% from the bottom.\n- Lots of breathing room.\n- Do not make it prominent.\n\nOVERALL COMPOSITION\n\nThe visual hierarchy should clearly be:\n\n1. “6-step generation”\n2. “Qwen-Image-2.1 ❤️ Viggle Turbo”\n3. flowing generated-image ribbon\n4. “DMD-distilled · Generate & Edit”\n5. small “Generate with viggle-turbo.” footer\n\nThe graphic should immediately communicate:\nfast generation, image generation, premium AI model, six-step inference.\n\nOverall aesthetic:\nminimal, elegant, expensive, technically sophisticated, cinematic, polished, restrained, premium AI launch campaign.\n\nAvoid:\n- excessive neon\n- cyberpunk look\n- too many thumbnails\n- busy collage layouts\n- random icons\n- fake UI elements\n- gradients inside every object\n- excessive lens flares\n- heavy shadows\n- 3D metallic typography\n- cartoon imagery\n- excessive text\n- logos other than the specified text\n- watermark\n- spelling errors\n- distorted letters\n- duplicated text",
|
| 27 |
-
"steps": 8,
|
| 28 |
-
"size_label": "3:2 · 2496×1664 (2048² area)",
|
| 29 |
-
"enhance": false,
|
| 30 |
-
"seed": 3
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"prompt": "Design a refined travel poster for a fictional night train. Render the headline exactly as \"THE MIDNIGHT EXPRESS\" and the subtitle \"A journey under the stars\". A silver train curves through dark blue mountains beneath a crescent moon. Art Deco geometry, ivory and gold lettering, clear typographic hierarchy, generous margins, print-ready composition.",
|
| 34 |
-
"refs": [
|
| 35 |
-
null,
|
| 36 |
-
null,
|
| 37 |
-
null
|
| 38 |
-
],
|
| 39 |
-
"result": "qwen_poster.png",
|
| 40 |
-
"info": "Pre-rendered example · seed `42` · 1664×2496 · 6 steps · v0.2.1 LoRA r256 · prompt sent as written (enhancement off)",
|
| 41 |
-
"used_prompt": "Design a refined travel poster for a fictional night train. Render the headline exactly as \"THE MIDNIGHT EXPRESS\" and the subtitle \"A journey under the stars\". A silver train curves through dark blue mountains beneath a crescent moon. Art Deco geometry, ivory and gold lettering, clear typographic hierarchy, generous margins, print-ready composition.",
|
| 42 |
-
"steps": 6,
|
| 43 |
-
"size_label": "2:3 · 1664×2496 (2048² area)",
|
| 44 |
-
"enhance": false,
|
| 45 |
-
"seed": 42
|
| 46 |
-
},
|
| 47 |
{
|
| 48 |
"prompt": "生成一张无缝的分镜插画,**现代真实偶像剧风格**(电影感写实摄影,柔和自然光与暖色调,浅景深虚化,韩系都市偶像剧质感,画面精致高级)。\n\n【版面(必须严格遵守)】\n- 恰好 6 个分镜格,**等宽**,排成**单独一横排(1 行 6 列)**;不是网格、不是两行,绝不要把任何一格再拆成上下两块。\n- 每格都是**竖长条矩形**(高明显大于宽,近似 9:16 竖条)。\n- 从左到右依次编号 1、2、3、4、5、6,每格左上角一个圆形数字徽标;**每个数字只出现一次,不重复、不跳号、不缺号。**\n- **每一格里都必须画出角色本人**在做该格的动作,角色占该格画面主体、完整清晰(半身或全身,约占该格高度 2/3 以上);**严禁出现只有背景、没有人物的空格。**\n- 6 格之间画风、光影氛围、人物一致。输出为一张扁平整图,6 格并排合并,不要输出多张分离文件。\n\n【角色】以输入参考图(含面部特写与正/侧/背三视全身立绘)为角色设计基准:现代年轻女性,棕色波浪长发带空气刘海,妆容清透,穿粉色方领修身长袖针织上衣、棕色灯芯绒过膝半裙配棕色皮带、棕色皮质机车靴。每一格里都是同一个人——面容、发型、服饰、身材比例保持一致,只改变姿势、表情、动作与所处场景;参考图仅定义外观,不要照搬其站姿。把角色自然地融入各自的真实场景中,透视比例正确、光影贴合。\n\n【逐格场景与内容】\n第1格:清晨阳光洒入的现代简约公寓,女孩站在落地窗边,双手捧着马克杯,望向窗外的城市天际线,神情恬静。\n第2格:白天繁华的都市街道人行道,两旁是时尚店铺橱窗和梧桐树,女孩背着单肩包边走边微微回头,浅浅微笑。\n第3格:文艺清新的咖啡馆靠窗卡座,女孩坐着低头看手机,嘴角带笑,窗外光线柔和,桌上放着一杯拿铁。\n第4格:暖色调的独立书店书架走廊,女孩踮脚从书架上抽出一本书,侧脸专注,光线温柔。\n第5格:傍晚金色晚霞下的城市人行天桥,女孩倚着栏杆回眸,背景是虚化的车流与高楼,暖光洒在脸上。\n第6格:夜晚霓虹灯光的街角,女孩仰头微笑看向前方,暖黄路灯与散景光斑环绕,都市夜景氛围。",
|
| 49 |
"refs": [
|
|
@@ -60,108 +15,108 @@
|
|
| 60 |
"seed": 42
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"prompt": "
|
| 64 |
"refs": [
|
| 65 |
null,
|
| 66 |
null,
|
| 67 |
null
|
| 68 |
],
|
| 69 |
-
"result": "
|
| 70 |
-
"info": "Pre-rendered example · seed `42` ·
|
| 71 |
-
"used_prompt": "
|
| 72 |
"steps": 6,
|
| 73 |
-
"size_label": "
|
| 74 |
"enhance": false,
|
| 75 |
"seed": 42
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"prompt": "
|
| 79 |
"refs": [
|
| 80 |
-
|
| 81 |
-
|
| 82 |
null
|
| 83 |
],
|
| 84 |
-
"result": "
|
| 85 |
-
"info": "Pre-rendered example · seed `42` ·
|
| 86 |
-
"used_prompt": "
|
| 87 |
"steps": 6,
|
| 88 |
-
"size_label": "
|
| 89 |
"enhance": false,
|
| 90 |
"seed": 42
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"prompt": "
|
| 94 |
"refs": [
|
| 95 |
null,
|
| 96 |
null,
|
| 97 |
null
|
| 98 |
],
|
| 99 |
-
"result": "
|
| 100 |
"info": "Pre-rendered example · seed `42` · 1664×2496 · 6 steps · v0.2.1 LoRA r256 · prompt sent as written (enhancement off)",
|
| 101 |
-
"used_prompt": "
|
| 102 |
"steps": 6,
|
| 103 |
"size_label": "2:3 · 1664×2496 (2048² area)",
|
| 104 |
"enhance": false,
|
| 105 |
"seed": 42
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"prompt": "
|
| 109 |
"refs": [
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
],
|
| 114 |
-
"result": "
|
| 115 |
-
"info": "Pre-rendered example · seed `
|
| 116 |
-
"used_prompt": "
|
| 117 |
"steps": 6,
|
| 118 |
-
"size_label": "
|
| 119 |
"enhance": true,
|
| 120 |
-
"seed":
|
| 121 |
},
|
| 122 |
{
|
| 123 |
-
"prompt": "
|
| 124 |
"refs": [
|
| 125 |
-
|
| 126 |
-
|
| 127 |
null
|
| 128 |
],
|
| 129 |
-
"result": "
|
| 130 |
-
"info": "Pre-rendered example · seed `
|
| 131 |
-
"used_prompt": "
|
| 132 |
"steps": 6,
|
| 133 |
-
"size_label": "
|
| 134 |
-
"enhance":
|
| 135 |
-
"seed":
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"prompt": "
|
| 139 |
"refs": [
|
| 140 |
-
|
| 141 |
null,
|
| 142 |
null
|
| 143 |
],
|
| 144 |
-
"result": "
|
| 145 |
-
"info": "Pre-rendered example · seed `3` ·
|
| 146 |
-
"used_prompt": "
|
| 147 |
-
"steps":
|
| 148 |
-
"size_label": "
|
| 149 |
-
"enhance":
|
| 150 |
"seed": 3
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"prompt": "
|
| 154 |
"refs": [
|
| 155 |
-
|
| 156 |
-
|
| 157 |
null
|
| 158 |
],
|
| 159 |
-
"result": "
|
| 160 |
-
"info": "Pre-rendered example · seed `42` ·
|
| 161 |
-
"used_prompt": "
|
| 162 |
"steps": 6,
|
| 163 |
-
"size_label": "
|
| 164 |
-
"enhance":
|
| 165 |
"seed": 42
|
| 166 |
}
|
| 167 |
]
|
|
|
|
| 1 |
[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
{
|
| 3 |
"prompt": "生成一张无缝的分镜插画,**现代真实偶像剧风格**(电影感写实摄影,柔和自然光与暖色调,浅景深虚化,韩系都市偶像剧质感,画面精致高级)。\n\n【版面(必须严格遵守)】\n- 恰好 6 个分镜格,**等宽**,排成**单独一横排(1 行 6 列)**;不是网格、不是两行,绝不要把任何一格再拆成上下两块。\n- 每格都是**竖长条矩形**(高明显大于宽,近似 9:16 竖条)。\n- 从左到右依次编号 1、2、3、4、5、6,每格左上角一个圆形数字徽标;**每个数字只出现一次,不重复、不跳号、不缺号。**\n- **每一格里都必须画出角色本人**在做该格的动作,角色占该格画面主体、完整清晰(半身或全身,约占该格高度 2/3 以上);**严禁出现只有背景、没有人物的空格。**\n- 6 格之间画风、光影氛围、人物一致。输出为一张扁平整图,6 格并排合并,不要输出多张分离文件。\n\n【角色】以输入参考图(含面部特写与正/侧/背三视全身立绘)为角色设计基准:现代年轻女性,棕色波浪长发带空气刘海,妆容清透,穿粉色方领修身长袖针织上衣、棕色灯芯绒过膝半裙配棕色皮带、棕色皮质机车靴。每一格里都是同一个人——面容、发型、服饰、身材比例保持一致,只改变姿势、表情、动作与所处场景;参考图仅定义外观,不要照搬其站姿。把角色自然地融入各自的真实场景中,透视比例正确、光影贴合。\n\n【逐格场景与内容】\n第1格:清晨阳光洒入的现代简约公寓,女孩站在落地窗边,双手捧着马克杯,望向窗外的城市天际线,神情恬静。\n第2格:白天繁华的都市街道人行道,两旁是时尚店铺橱窗和梧桐树,女孩背着单肩包边走边微微回头,浅浅微笑。\n第3格:文艺清新的咖啡馆靠窗卡座,女孩坐着低头看手机,嘴角带笑,窗外光线柔和,桌上放着一杯拿铁。\n第4格:暖色调的独立书店书架走廊,女孩踮脚从书架上抽出一本书,侧脸专注,光线温柔。\n第5格:傍晚金色晚霞下的城市人行天桥,女孩倚着栏杆回眸,背景是虚化的车流与高楼,暖光洒在脸上。\n第6格:夜晚霓虹灯光的街角,女孩仰头微笑看向前方,暖黄路灯与散景光斑环绕,都市夜景氛围。",
|
| 4 |
"refs": [
|
|
|
|
| 15 |
"seed": 42
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"prompt": "这是一张带有透明度的RGBA格式图像,呈现一位身着华丽婚纱的动漫风格女性角色。画面中无任何可识别的文字信息。角色为年轻女性,拥有白皙肌肤、红润脸颊与明亮红色眼眸,面带温柔微笑,表情甜美而幸福。她头戴精致银色皇冠与白色蕾丝头纱,金色长发自然垂落肩头,发丝柔顺且富有光泽。身穿多层荷叶边设计的粉白渐变抹胸婚纱,裙摆蓬松飘逸,层次丰富,材质轻盈如花瓣般展开;胸前手持一束由白色玫瑰与绿色叶片组成的捧花,花束饱满,绿叶点缀其间,增添清新感。双腿修长,穿着透明薄纱质感的过膝袜与饰有玫瑰图案的白色高跟鞋,姿态优雅站立,双手轻握捧花置于腹前。整体构图为全身正面视角,色彩柔和梦幻,以粉、白、绿为主色调,光影细腻,具有典型的日系二次元插画美学风格,适用于游戏立绘、视觉小说或数字艺术收藏等场景。 该图像具有alpha通道,背景是透明的。",
|
| 19 |
"refs": [
|
| 20 |
null,
|
| 21 |
null,
|
| 22 |
null
|
| 23 |
],
|
| 24 |
+
"result": "qwen_rgba_bride.png",
|
| 25 |
+
"info": "Pre-rendered example · seed `42` · 1664×2496 · 6 steps · v0.2.1 LoRA r256 · prompt sent as written (enhancement off)",
|
| 26 |
+
"used_prompt": "这是一张带有透明度的RGBA格式图像,呈现一位身着华丽婚纱的动漫风格女性角色。画面中无任何可识别的文字信息。角色为年轻女性,拥有白皙肌肤、红润脸颊与明亮红色眼眸,面带温柔微笑,表情甜美而幸福。她头戴精致银色皇冠与白色蕾丝头纱,金色长发自然垂落肩头,发丝柔顺且富有光泽。身穿多层荷叶边设计的粉白渐变抹胸婚纱,裙摆蓬松飘逸,层次丰富,材质轻盈如花瓣般展开;胸前手持一束由白色玫瑰与绿色叶片组成的捧花,花束饱满,绿叶点缀其间,增添清新感。双腿修长,穿着透明薄纱质感的过膝袜与饰有玫瑰图案的白色高跟鞋,姿态优雅站立,双手轻握捧花置于腹前。整体构图为全身正面视角,色彩柔和梦幻,以粉、白、绿为主色调,光影细腻,具有典型的日系二次元插画美学风格,适用于游戏立绘、视觉小说或数字艺术收藏等场景。 该图像具有alpha通道,背景是透明的。",
|
| 27 |
"steps": 6,
|
| 28 |
+
"size_label": "2:3 · 1664×2496 (2048² area)",
|
| 29 |
"enhance": false,
|
| 30 |
"seed": 42
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"prompt": "An elegant fashion-magazine style infographic, landscape 16:9: a character style file for an original fictional heroine named Mira Solenne. Warm ivory paper background with a faint watercolor texture, thin champagne-gold hairlines dividing the panels, generous white space, refined high-contrast serif headings and small clean sans-serif labels. Palette: midnight navy, pearl white, silver grey, dusty lilac and champagne gold.\n\nTop banner: a large serif title \"MOONLIGHT SILK\" on the left with a short gold rule beneath it, and on the right in small letter-spaced caps \"VOL.05 · STYLE FILE\".\n\nCenter column (the largest area): a full-body watercolor and ink fashion illustration of Mira Solenne, a young woman with a sleek silver-lilac bob, in a flowing midnight-navy silk slip dress under a cropped pearl-white jacket, silver strappy heels, standing in a graceful pose, a soft lilac watercolor wash and a pale crescent moon behind her. Below her feet, her name in a small italic serif: \"Mira Solenne\".\n\nLeft column, top: a panel headed \"PROFILE\" with four lines: \"Style: Modern Romantic\", \"Height: 172 cm\", \"Colors: Navy & Pearl\", \"Mood: Calm & Dreamy\".\nLeft column, bottom: a panel headed \"DETAILS\" with four small line-art icons in a 2×2 grid, captioned \"Pearl Earrings\", \"Silk Scarf\", \"Moon Clutch\", \"Silver Heels\".\n\nRight column, top: a panel headed \"PALETTE\" with a row of six round color swatches captioned \"Midnight\", \"Pearl\", \"Silver\", \"Lilac\", \"Gold\", \"Ink\".\nRight column, middle: a panel headed \"STYLE RADAR\" with a pentagon radar chart filled in translucent lilac, five axes labeled \"Elegance 92%\", \"Romance 88%\", \"Comfort 76%\", \"Minimal 70%\", \"Edge 64%\".\nRight column, bottom: a panel headed \"3 LOOKS\" with three small watercolor sketches of her: in a navy gown captioned \"Gala Night\", in a white trench coat captioned \"City Walk\", in a lilac dress and straw hat captioned \"Sunday Brunch\".\n\nBottom strip across the full width: five rounded outline keyword chips with gold borders, \"Satin\", \"Moonlit\", \"Soft Tailoring\", \"Quiet Luxury\", \"Night Garden\".",
|
| 34 |
"refs": [
|
| 35 |
+
null,
|
| 36 |
+
null,
|
| 37 |
null
|
| 38 |
],
|
| 39 |
+
"result": "t2i_style_file.png",
|
| 40 |
+
"info": "Pre-rendered example · seed `42` · 2720×1536 · 6 steps · v0.2.1 LoRA r256 · prompt sent as written (enhancement off)",
|
| 41 |
+
"used_prompt": "An elegant fashion-magazine style infographic, landscape 16:9: a character style file for an original fictional heroine named Mira Solenne. Warm ivory paper background with a faint watercolor texture, thin champagne-gold hairlines dividing the panels, generous white space, refined high-contrast serif headings and small clean sans-serif labels. Palette: midnight navy, pearl white, silver grey, dusty lilac and champagne gold.\n\nTop banner: a large serif title \"MOONLIGHT SILK\" on the left with a short gold rule beneath it, and on the right in small letter-spaced caps \"VOL.05 · STYLE FILE\".\n\nCenter column (the largest area): a full-body watercolor and ink fashion illustration of Mira Solenne, a young woman with a sleek silver-lilac bob, in a flowing midnight-navy silk slip dress under a cropped pearl-white jacket, silver strappy heels, standing in a graceful pose, a soft lilac watercolor wash and a pale crescent moon behind her. Below her feet, her name in a small italic serif: \"Mira Solenne\".\n\nLeft column, top: a panel headed \"PROFILE\" with four lines: \"Style: Modern Romantic\", \"Height: 172 cm\", \"Colors: Navy & Pearl\", \"Mood: Calm & Dreamy\".\nLeft column, bottom: a panel headed \"DETAILS\" with four small line-art icons in a 2×2 grid, captioned \"Pearl Earrings\", \"Silk Scarf\", \"Moon Clutch\", \"Silver Heels\".\n\nRight column, top: a panel headed \"PALETTE\" with a row of six round color swatches captioned \"Midnight\", \"Pearl\", \"Silver\", \"Lilac\", \"Gold\", \"Ink\".\nRight column, middle: a panel headed \"STYLE RADAR\" with a pentagon radar chart filled in translucent lilac, five axes labeled \"Elegance 92%\", \"Romance 88%\", \"Comfort 76%\", \"Minimal 70%\", \"Edge 64%\".\nRight column, bottom: a panel headed \"3 LOOKS\" with three small watercolor sketches of her: in a navy gown captioned \"Gala Night\", in a white trench coat captioned \"City Walk\", in a lilac dress and straw hat captioned \"Sunday Brunch\".\n\nBottom strip across the full width: five rounded outline keyword chips with gold borders, \"Satin\", \"Moonlit\", \"Soft Tailoring\", \"Quiet Luxury\", \"Night Garden\".",
|
| 42 |
"steps": 6,
|
| 43 |
+
"size_label": "16:9 · 2720×1536 (2048² area)",
|
| 44 |
"enhance": false,
|
| 45 |
"seed": 42
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"prompt": "Design a refined travel poster for a fictional night train. Render the headline exactly as \"THE MIDNIGHT EXPRESS\" and the subtitle \"A journey under the stars\". A silver train curves through dark blue mountains beneath a crescent moon. Art Deco geometry, ivory and gold lettering, clear typographic hierarchy, generous margins, print-ready composition.",
|
| 49 |
"refs": [
|
| 50 |
null,
|
| 51 |
null,
|
| 52 |
null
|
| 53 |
],
|
| 54 |
+
"result": "qwen_poster.png",
|
| 55 |
"info": "Pre-rendered example · seed `42` · 1664×2496 · 6 steps · v0.2.1 LoRA r256 · prompt sent as written (enhancement off)",
|
| 56 |
+
"used_prompt": "Design a refined travel poster for a fictional night train. Render the headline exactly as \"THE MIDNIGHT EXPRESS\" and the subtitle \"A journey under the stars\". A silver train curves through dark blue mountains beneath a crescent moon. Art Deco geometry, ivory and gold lettering, clear typographic hierarchy, generous margins, print-ready composition.",
|
| 57 |
"steps": 6,
|
| 58 |
"size_label": "2:3 · 1664×2496 (2048² area)",
|
| 59 |
"enhance": false,
|
| 60 |
"seed": 42
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"prompt": "The person from image 1 is petting the cat from image 2, the bird from image 3 is next to them",
|
| 64 |
"refs": [
|
| 65 |
+
"woman1.webp",
|
| 66 |
+
"cat_window.webp",
|
| 67 |
+
"bird.webp"
|
| 68 |
],
|
| 69 |
+
"result": "edit_3ref_klein.png",
|
| 70 |
+
"info": "Pre-rendered example · seed `42` · 928×1152 · 6 steps · v0.2.1 LoRA r256 · prompt enhanced",
|
| 71 |
+
"used_prompt": "Compose a scene where the person from <image1>, standing beside the vintage brown car, is gently petting the fluffy cat from <image2> that is perched on a stone windowsill with green shutters, while the bird from <image3>, with a red crown and long beak, stands next to them, all under warm cinematic lighting with a shallow depth of field focusing on the trio, keeping the background and subjects' identities from the input images unchanged.",
|
| 72 |
"steps": 6,
|
| 73 |
+
"size_label": "Auto · match the last reference (1024² area)",
|
| 74 |
"enhance": true,
|
| 75 |
+
"seed": 42
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"prompt": "图中画圈标注的地方需要补上一名骑坐姿态的西部牛仔男子。他头戴棕色宽檐牛仔帽,蓄着浓密的络腮胡,脸侧向画面左方;上身穿棕色帆布夹克,里面搭配深蓝色牛仔衬衫,颈间系着浅棕色围巾;下身穿着带流苏的棕色皮质护腿,脚穿皮靴踩进马镫,一只手搭在鞍部附近,整体呈现自然的骑乘状态。",
|
| 79 |
"refs": [
|
| 80 |
+
"qwen_mask_edit_in1.webp",
|
| 81 |
+
"qwen_mask_edit_in2.webp",
|
| 82 |
null
|
| 83 |
],
|
| 84 |
+
"result": "qwen_mask_edit.png",
|
| 85 |
+
"info": "Pre-rendered example · seed `42` · 1248×1888 · 6 steps · v0.2.1 LoRA r256 · prompt sent as written (enhancement off)",
|
| 86 |
+
"used_prompt": "图中画圈标注的地方需要补上一名骑坐姿态的西部牛仔男子。他头戴棕色宽檐牛仔帽,蓄着浓密的络腮胡,脸侧向画面左方;上身穿棕色帆布夹克,里面搭配深蓝色牛仔衬衫,颈间系着浅棕色围巾;下身穿着带流苏的棕色皮质护腿,脚穿皮靴踩进马镫,一只手搭在鞍部附近,整体呈现自然的骑乘状态。",
|
| 87 |
"steps": 6,
|
| 88 |
+
"size_label": "2:3 · 1248×1888 (1536² area)",
|
| 89 |
+
"enhance": false,
|
| 90 |
+
"seed": 42
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"prompt": "Create a premium, minimalist launch graphic for an AI image model, designed for a Twitter/X announcement.\n\nAspect ratio: 16:9.\nStyle: elegant, high-end, modern AI product launch visual. Clean Apple / NVIDIA / premium creative-software aesthetic. Dark, cinematic, sophisticated, not flashy or cluttered.\n\nBACKGROUND\n- Deep black to charcoal gradient background.\n- Very subtle blue and violet ambient glow.\n- Soft cinematic lighting, slight glossy reflections near the bottom.\n- Large areas of negative space.\n- No unnecessary particles, grids, icons, decorative UI, or busy textures.\n\nTOP-LEFT TYPOGRAPHY\n\nMain title:\n“Qwen-Image-2.1 ❤️ Viggle Turbo”\n\n- Large bold geometric sans-serif.\n- Clean Swiss-style typography.\n- Bright soft-white text.\n- Red heart between the two model names.\n- Precise kerning and professional spacing.\n- Keep the title on one line.\n- Position around 4–5% from the left and 8–10% from the top.\n\nDirectly underneath, smaller subtitle:\n“DMD-distilled · Generate & Edit”\n\n- Thin or regular sans-serif.\n- Around 30–35% of the main title font size.\n- Soft light-gray / off-white.\n- Generous letter spacing.\n- Minimal and understated.\n\nCENTER HERO MESSAGE\n\nLarge dominant typography:\n\n“6-step”\n“generation”\n\non two lines.\n\n- “6-step” should be extremely large.\n- “generation” slightly smaller but still bold.\n- Heavy geometric sans-serif.\n- White / very subtle cool-white gradient.\n- Tight line spacing.\n- Perfectly clean typography.\n- Position slightly above the vertical center.\n- The text should be the strongest visual element in the design.\n- No exaggerated 3D text, extrusion, chrome effects, or heavy shadows.\n- Only a very subtle soft glow.\n\nVISUAL ELEMENT\n\nCreate a single elegant curved ribbon of generated images flowing across the lower half of the composition.\n\nThe ribbon should:\n- Start from the lower-left foreground.\n- Curve smoothly toward the center-right.\n- Continue upward toward the upper-right background.\n- Feel like a sophisticated cinematic film strip or flowing image-generation sequence.\n- Use approximately 5–7 image panels only.\n- Avoid a dense collage.\n\nEach panel:\n- Rounded rectangle.\n- Thin subtle border.\n- Premium glossy display appearance.\n- Slight perspective distortion following the curve.\n- Gradually decrease in size toward the background.\n- Use realistic generated landscape photography:\n • alpine lake\n • mountain valley\n • waterfall\n • dramatic mountain peaks\n • coastal sunset\n- Rich but natural colors.\n- Foreground panels sharp, distant panels progressively softer / slightly blurred.\n- Strong depth-of-field.\n\nThe ribbon itself should have an extremely subtle luminous edge:\n- cyan / electric blue on the left\n- transitioning gently toward violet / magenta on the right\n\nKeep the glow restrained and premium.\nDo not make it look like cyberpunk neon.\n\nLIGHTING\n\nAdd one very thin horizontal blue-to-violet light flare passing subtly behind the “6-step” text.\n\nUse soft reflected blue/violet light underneath the image ribbon.\n\nLighting should feel cinematic and expensive, not game-like.\n\nBOTTOM-RIGHT\n\nSmall footer:\n“Generate with viggle-turbo”\n\n- Small clean sans-serif.\n- White / light gray.\n- Bottom-right aligned.\n- Approximately 5% from the right and 6–8% from the bottom.\n- Lots of breathing room.\n- Do not make it prominent.\n\nOVERALL COMPOSITION\n\nThe visual hierarchy should clearly be:\n\n1. “6-step generation”\n2. “Qwen-Image-2.1 ❤️ Viggle Turbo”\n3. flowing generated-image ribbon\n4. “DMD-distilled · Generate & Edit”\n5. small “Generate with viggle-turbo.” footer\n\nThe graphic should immediately communicate:\nfast generation, image generation, premium AI model, six-step inference.\n\nOverall aesthetic:\nminimal, elegant, expensive, technically sophisticated, cinematic, polished, restrained, premium AI launch campaign.\n\nAvoid:\n- excessive neon\n- cyberpunk look\n- too many thumbnails\n- busy collage layouts\n- random icons\n- fake UI elements\n- gradients inside every object\n- excessive lens flares\n- heavy shadows\n- 3D metallic typography\n- cartoon imagery\n- excessive text\n- logos other than the specified text\n- watermark\n- spelling errors\n- distorted letters\n- duplicated text",
|
| 94 |
"refs": [
|
| 95 |
+
null,
|
| 96 |
null,
|
| 97 |
null
|
| 98 |
],
|
| 99 |
+
"result": "t2i_launch.png",
|
| 100 |
+
"info": "Pre-rendered example · seed `3` · 2496×1664 · 8 steps · v0.2.1 LoRA r256 · prompt sent as written (enhancement off)",
|
| 101 |
+
"used_prompt": "Create a premium, minimalist launch graphic for an AI image model, designed for a Twitter/X announcement.\n\nAspect ratio: 16:9.\nStyle: elegant, high-end, modern AI product launch visual. Clean Apple / NVIDIA / premium creative-software aesthetic. Dark, cinematic, sophisticated, not flashy or cluttered.\n\nBACKGROUND\n- Deep black to charcoal gradient background.\n- Very subtle blue and violet ambient glow.\n- Soft cinematic lighting, slight glossy reflections near the bottom.\n- Large areas of negative space.\n- No unnecessary particles, grids, icons, decorative UI, or busy textures.\n\nTOP-LEFT TYPOGRAPHY\n\nMain title:\n“Qwen-Image-2.1 ❤️ Viggle Turbo”\n\n- Large bold geometric sans-serif.\n- Clean Swiss-style typography.\n- Bright soft-white text.\n- Red heart between the two model names.\n- Precise kerning and professional spacing.\n- Keep the title on one line.\n- Position around 4–5% from the left and 8–10% from the top.\n\nDirectly underneath, smaller subtitle:\n“DMD-distilled · Generate & Edit”\n\n- Thin or regular sans-serif.\n- Around 30–35% of the main title font size.\n- Soft light-gray / off-white.\n- Generous letter spacing.\n- Minimal and understated.\n\nCENTER HERO MESSAGE\n\nLarge dominant typography:\n\n“6-step”\n“generation”\n\non two lines.\n\n- “6-step” should be extremely large.\n- “generation” slightly smaller but still bold.\n- Heavy geometric sans-serif.\n- White / very subtle cool-white gradient.\n- Tight line spacing.\n- Perfectly clean typography.\n- Position slightly above the vertical center.\n- The text should be the strongest visual element in the design.\n- No exaggerated 3D text, extrusion, chrome effects, or heavy shadows.\n- Only a very subtle soft glow.\n\nVISUAL ELEMENT\n\nCreate a single elegant curved ribbon of generated images flowing across the lower half of the composition.\n\nThe ribbon should:\n- Start from the lower-left foreground.\n- Curve smoothly toward the center-right.\n- Continue upward toward the upper-right background.\n- Feel like a sophisticated cinematic film strip or flowing image-generation sequence.\n- Use approximately 5–7 image panels only.\n- Avoid a dense collage.\n\nEach panel:\n- Rounded rectangle.\n- Thin subtle border.\n- Premium glossy display appearance.\n- Slight perspective distortion following the curve.\n- Gradually decrease in size toward the background.\n- Use realistic generated landscape photography:\n • alpine lake\n • mountain valley\n • waterfall\n • dramatic mountain peaks\n • coastal sunset\n- Rich but natural colors.\n- Foreground panels sharp, distant panels progressively softer / slightly blurred.\n- Strong depth-of-field.\n\nThe ribbon itself should have an extremely subtle luminous edge:\n- cyan / electric blue on the left\n- transitioning gently toward violet / magenta on the right\n\nKeep the glow restrained and premium.\nDo not make it look like cyberpunk neon.\n\nLIGHTING\n\nAdd one very thin horizontal blue-to-violet light flare passing subtly behind the “6-step” text.\n\nUse soft reflected blue/violet light underneath the image ribbon.\n\nLighting should feel cinematic and expensive, not game-like.\n\nBOTTOM-RIGHT\n\nSmall footer:\n“Generate with viggle-turbo”\n\n- Small clean sans-serif.\n- White / light gray.\n- Bottom-right aligned.\n- Approximately 5% from the right and 6–8% from the bottom.\n- Lots of breathing room.\n- Do not make it prominent.\n\nOVERALL COMPOSITION\n\nThe visual hierarchy should clearly be:\n\n1. “6-step generation��\n2. “Qwen-Image-2.1 ❤️ Viggle Turbo”\n3. flowing generated-image ribbon\n4. “DMD-distilled · Generate & Edit”\n5. small “Generate with viggle-turbo.” footer\n\nThe graphic should immediately communicate:\nfast generation, image generation, premium AI model, six-step inference.\n\nOverall aesthetic:\nminimal, elegant, expensive, technically sophisticated, cinematic, polished, restrained, premium AI launch campaign.\n\nAvoid:\n- excessive neon\n- cyberpunk look\n- too many thumbnails\n- busy collage layouts\n- random icons\n- fake UI elements\n- gradients inside every object\n- excessive lens flares\n- heavy shadows\n- 3D metallic typography\n- cartoon imagery\n- excessive text\n- logos other than the specified text\n- watermark\n- spelling errors\n- distorted letters\n- duplicated text",
|
| 102 |
+
"steps": 8,
|
| 103 |
+
"size_label": "3:2 · 2496×1664 (2048² area)",
|
| 104 |
+
"enhance": false,
|
| 105 |
"seed": 3
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"prompt": "Photograph a translucent emerald perfume bottle on pale limestone beside a shallow pool. Rippling sunlight reflects through the glass onto the stone. A single olive branch frames the upper left corner. Luxury product photography, realistic refraction, crisp bottle edges, soft shadows, uncluttered composition, no logo or text.",
|
| 109 |
"refs": [
|
| 110 |
+
null,
|
| 111 |
+
null,
|
| 112 |
null
|
| 113 |
],
|
| 114 |
+
"result": "qwen_perfume.png",
|
| 115 |
+
"info": "Pre-rendered example · seed `42` · 2496×1664 · 6 steps · v0.2.1 LoRA r256 · prompt sent as written (enhancement off)",
|
| 116 |
+
"used_prompt": "Photograph a translucent emerald perfume bottle on pale limestone beside a shallow pool. Rippling sunlight reflects through the glass onto the stone. A single olive branch frames the upper left corner. Luxury product photography, realistic refraction, crisp bottle edges, soft shadows, uncluttered composition, no logo or text.",
|
| 117 |
"steps": 6,
|
| 118 |
+
"size_label": "3:2 · 2496×1664 (2048² area)",
|
| 119 |
+
"enhance": false,
|
| 120 |
"seed": 42
|
| 121 |
}
|
| 122 |
]
|
examples/t2i_style_file.png
ADDED
|
Git LFS Details
|