Ciao

1.5K posts

Ciao banner
Ciao

Ciao

@goatjop

家有柴,早起遛,迷迷糊

ShangHai Katılım Şubat 2013
3.5K Takip Edilen322 Takipçiler
Ciao retweetledi
INK
INK@0xInk_·
To finish first, first you must finish. made with Midjourney v8.1 and Seedance2
English
75
213
2.8K
98.3K
Ciao retweetledi
Larus Canus
Larus Canus@MrLarus·
🤯太震撼了! 我用ChatGPT-Image2全新生成《3D历史人物立像档案》,气场爆炸!🔥 把一个人的一生,浓缩成一座可以阅读的历史立像: 诸葛亮、王阳明、张居正、曾国藩 中央是全身3D人物,手中的书卷破框而出 一生高光画面散落在时光碎片里,人物立体气场逼人! 提示词参考评论区👇
Larus Canus tweet mediaLarus Canus tweet mediaLarus Canus tweet mediaLarus Canus tweet media
中文
681
189
1.1K
172.4K
Ciao retweetledi
Abdul Șhakoor
Abdul Șhakoor@abxxai·
What AI is doing right now is insane.🤯 ChatGPT Image 2 turns your ideas into full storyboards with cast and scenes… then Seedance 2 turns those into full cinematic shots. Exact prompts below 👇
English
33
80
532
29.9K
Ciao retweetledi
Beginnersblog
Beginnersblog@beginnersblog1·
GPT Image 2 + Seedance 2 = cartoon chase scene. I wanted to see how far I could push storyboard-to-video consistency, so I created a full 15-second cat vs mouse sequence inside a completely destroyed house. The process was actually simple: - generated a 3x3 cinematic storyboard sheet in GPT Image 2 - designed every frame like a real animation pre-production sketch - added camera directions, motion cues, timing notes, and destruction progression - used Seedance 2 to animate the entire sequence into one continuous cinematic shot flow What surprised me most was how well Seedance 2.0 understood the visual continuity between frames. The flying debris, motion blur, exaggerated jumps, and camera movement felt surprisingly cohesive. . . .
English
31
116
927
36.6K
Ciao retweetledi
Okan Can
Okan Can@0kncn·
GPT Image 2 ile storyboard çizdim, sonra Seedance 2.0 ile bunu tam animasyon sahnesine çevirdim Bir rakun. Bir donut. Ve tamamen kontrolden çıkan çizgi film kaosu. Storyboard → cinematic cartoon video dönüşümü gerçekten deli hissettiriyor. AI artık sadece görsel üretmiyor, timing ve slapstick komedi de kurabiliyor Ve en absürt kısmı: Bunun tamamını sadece 10 dakikada yaptım.
Türkçe
242
745
5.8K
623.1K
Ciao retweetledi
Kōda
Kōda@aimikoda·
GPT Image 2 + Seedance 2.0 Prompt Share Tried using IPA + FACS for a contemporary performance piece where live singing and choreography happen simultaneously. Not sure how much of it actually worked technically but I think the final result turned out pretty interesting. I also ended up color-coding the storyboard annotations because otherwise annotations were confusing the model. Different colors helped separate body movement, camera motion, framing and lighting directions from the actual environment and character drawings. You can find color-coded storyboard prompt + seedance 2.0 prompt in the replies.
English
87
293
2K
113.3K
Ciao retweetledi
Dilum Sanjaya
Dilum Sanjaya@DilumSanjaya·
Fun interactive science app ideas | Part 3 Played around with generating 3D biological structures and made an app to explore them interactively UI Design GPT Images 2 Code Gemini 3.1 Pro More demos ↓
English
516
2.1K
17.1K
2.2M
Ciao retweetledi
古一
古一@MANISH1027512·
现在我生图基本都交给 Codex 了,尤其是各种自动化任务。 昨天一天,它给我跑了 300 多张图。 但有个问题:这些图默认都会存在 Codex 的本地生成目录里,而我平时管理图片、视频、参考素材,主要都在 Eagle 里。 正好 Eagle 提供了 MCP,可以让 Agent 操作 Eagle App 里的大部分能力。 所以我干脆写了一个 Skill:codex-image-to-eagle 它主要有两种用法: 1.手动调用 比如直接对 Agent 说: “帮我把今天所有 Codex 生成的图归档到 Eagle。” 2.自动调用 在自动化生图任务里加一个 hook:每生成一张图,就自动归档到 Eagle。 归档时会自动按日期分类,更重要的是: 每张图对应的 prompt 也会一起写进 Eagle 注释里。 这样之后翻图、复盘、找提示词、做二次创作,就不用再到处翻文件夹了。 我已经把这个 Skill 开源了: github.com/vibeshotclub/v… 你可以直接让自己的 Agent 安装,基本开箱即用。 前提是:你得有 Eagle,并且开启 Eagle MCP。 如果你还不知道 Eagle 是什么,建议你了解一下。 这几乎是我们社群里玩 AIGC 的人手一个的本地图片 / 视频资源管理神器。
古一 tweet media古一 tweet media
古一@MANISH1027512

什么是自动化内容工厂? 在codex中设置自动化10分钟跑一次,每次3张,风格高度统一,但每一张却完全不一样,所有元素都会打乱重组,张张出片,张张有惊喜。 这套模板很快会上架到vibeshot.club,敬请期待。

中文
46
103
720
185.5K
Ciao retweetledi
Kashberg
Kashberg@Kashberg_0·
GPT IMAGE 2 & Seedance 2.0 That’s so awesome 🔥
Kashberg tweet media
English
37
139
1.2K
94.6K
Ciao retweetledi
KANA
KANA@KanaWorks_AI·
ChatGPT-Image-2.0 × Seedance 2.0|ゲームUI切り替え🐰 まさかAIでここまでのUI切り替えができるとは思わなかった。ChatGPT-Image-2.0でのUIデザインはすでにかなり精度が高い。 Seedance 2.0で動画化する段階ではまだ課題あり。「操作レベル」での精密なコントロールは依然として難しい。 AEやUnityなら一度フローを構築すれば安定して再現できるが、AIはまだ「生成ベース」で、言語だけで結果を完全に固定するのは難しい。 それでも効率は確実に上がっている。 以前はUI一式を組むのに最低でも1週間。 今回は初回でも約3時間で一通り完成。 100%の一致を求めなければ、その後の再現はかなり速い。 PPTやプロダクトデモ用途なら、すでに十分実用レベル。 ゲーム業界、変わり始めている🤯 GPT Image 2.0 × Seedance 2.0 on @higgsfield
KANA@KanaWorks_AI

ChatGPT-Image-2.0 × Seedance 2.0 アクション系ゲーム: ハメ技 🤣 作り方: Step 1:ChatGPT-Image-2.0で画面を生成 Prompt ➕ image Generate a Boss battle game screenshot inspired by (a certain movie, a certain game, a certain style). Third-person perspective. The protagonist is named (Character 1), with the weapon (frying pan). In the item bar, there is a healing (gourd), and another item is (poison darts). The Boss is image2, named (Character 2), with the weapon (vajra). The scene is set at (the entrance of ruins in an open forest). Step 2:Seedance 2.0で動画化 Prompt Share 122 Cinematic action combat game visuals, presented in a single continuous shot. Highly immersive, fast-paced, with extremely impactful combat feedback. The protagonist is Rabbit KANA, wielding a (frying pan). The Boss is White Tiger Ascetic, wielding a (vajra). [Environment] An ancient, ruined stone battlefield. The ground is covered with cracks and scattered debris. Dust and thin mist float in the air. The overall tone is dark, with high-contrast lighting, strong volumetric light and particle effects. A gentle wind flows through the scene, creating an oppressive yet epic atmosphere. [Opening – Ranged Probe] A white rabbit adventurer crouches on a distant high ground, wearing a yellow jacket. The rabbit rapidly throws three daggers emitting green smoke toward the distant White Tiger Boss. The daggers strike the Boss’s body, bursting into green smoke. The White Tiger triggers hit reactions and sound effects. [Battle Trigger] The rabbit leaps down from the high ground, with the camera following the fast descent, landing directly in front of the Boss. The rabbit draws its weapon — a frying pan. War drums begin, and Boss battle music starts. A health bar appears above the White Tiger. The rabbit slowly circles the Boss. [High-Speed Melee] Both sides instantly engage in high-speed melee combat. The White Tiger swings the vajra with heavy, powerful motions, generating strong visual effects and shockwaves. The rabbit rolls forward into close range and delivers precise attacks with the frying pan. The White Tiger’s health decreases. The White Tiger retaliates with sweeping, slashing, and heavy strikes using the vajra, while the rabbit performs multiple precise parries. [Parry & Opening] The rabbit seizes the moment and executes a perfect parry, triggering a powerful impact sound and visual feedback. The Boss enters a staggered state, freezing briefly before dropping to one knee. [Execution Animation] The rabbit leaps into the air above the White Tiger and unleashes its ultimate attack. The frying pan channels overwhelming thunder as a massive lightning dragon descends from the sky. Lightning and the frying pan strike simultaneously. The rabbit lands calmly with its back to the camera. Behind it, the White Tiger collapses with a heavy crash, kicking up dust and debris. [Final Frame] At the center of the screen, large red calligraphic text appears: “勝” [Technical Specifications] Hyper-realistic, cinematic lighting, 8K resolution, 30fps, no subtitles, no watermark, only essential UI elements retained. Rich details, dynamic camera, motion blur, strong composition. ゲームをプレイする中で、世界を探索したり、さまざまな遊び方を発見したりすることは大きな楽しみの一つです。実は、AI生成も同じです。AIと対戦し、協力するような、とても面白いゲームです。皆さんが楽しく遊べることを願っています🐰❤️‍🔥

日本語
6
27
230
14.3K
Ciao retweetledi
Vigo Zhao
Vigo Zhao@VigoCreativeAI·
昨天很多人问我: 这组「毛绒城市节日海报」到底是怎么做出来的? 答案不是一句 prompt。 我真正用的是: 参考图 → 风格拆解 → JSON 化 → 换主题批量生成 今天把这个方法讲清楚。 想要最后那份「风格 JSON + 通用 Prompt 模板」的话,先收藏,这条看到最后。 👇
Vigo Zhao tweet mediaVigo Zhao tweet mediaVigo Zhao tweet mediaVigo Zhao tweet media
Vigo Zhao@VigoCreativeAI

最近看到一张韩国节日海报,第一眼就被抓住了。 不是因为构图多复杂,而是它把“城市旅游海报”做成了一个巨型毛绒玩具世界。 于是我把原图风格提取成 JSON,再用同一套视觉语言生成了两张新图: Cherry Market Day 和 Harbor Light Fest。 这个风格真的很适合做城市活动视觉。 👇

中文
17
172
1.3K
106.3K
Ciao retweetledi
Justine Moore
Justine Moore@venturetwins·
Generated this video by chatting with a single agent ✨ I told @heyglif that I wanted to create this anime short. It made the storyboard with GPT-Image-2 and then animated it with Seedance 2. Such an easy way to get controllable video generation!
English
67
108
951
74.9K
Ciao retweetledi
Min Zhou
Min Zhou@fMinZhou·
GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this
English
66
485
4.4K
338.1K
Ciao retweetledi
Zain Shah
Zain Shah@zan2434·
Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see. @eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)
English
1.1K
3.6K
28.1K
5.8M
Ciao retweetledi
Dev Ed
Dev Ed@developedbyed·
Making an app in electron to generate your own game assets,tiles,animations, inpainting and more. No subscriptions, all run locally
English
180
329
4.9K
292.6K
Ciao retweetledi
Viktor Oddy
Viktor Oddy@viktoroddy·
Gemini vs Claude Claude has started to get really damn good at design. Prompt below ↓
English
47
141
2.2K
184.2K
Ciao retweetledi
探险李
探险李@TanXianli_X·
从修车工到年入 7 亿的机车老板 下面的 15 分钟视频值得好好看看 张雪机车创始人- 张雪 玩摩托车的应该都知道 19 岁开十八手摩托追记者 3 小时 就是为了上电视求个进车队的机会 谁能想到他后来干出这么大的动静? 财富是靠自己一步一步打拼的,不是等?
中文
109
235
1.1K
426.3K
Ciao retweetledi
Elon Musk
Elon Musk@elonmusk·
Starship flies again next month
English
16.2K
33K
439.1K
73.6M