petersalon33

nature

[petersalon33 @191072577]

WHEN THE SUN IS GONE, THE CLAP REMAINS https://t.co/5fMrxV4i0F 來自 @YouTube What if the Maya discovered Europe in 1492?
The Vikings became "northern indigenous people." They live in a cultural reserve, wear animal skins, and perform war chants for Maya tourists.

[petersalon33 @191072577]

BRONZE SILENCE I : SANXINGDUI https://t.co/pWpu5Fsq4t 來自 @YouTube

[petersalon33 @191072577]

Bronze Silence II: The Conquest https://t.co/jugNtUSpcI 來自 @YouTube

[petersalon33 @191072577]

Where the dark bird descended,
armies rose.

Three thousand marched west.
Not all came back.

The oracle bone cracked—
the fracture pointed west.

The wind will not speak.
The earth will not speak.
The bronze will not speak.

[petersalon33 @191072577]

At the very moment the Trojan War was raging across the sea, a woman led 13,000 soldiers into the desert. No Homer sang for her. Only oracle bones remembered.

[petersalon33 @191072577]

3,000 years later, the masks still have no answer.

When a civilization chooses silence,
the bronze remembers.

— Bronze Silence

[petersalon33 @191072577]

An ai generated story explains how does SAN XINDUI Civilization disappears

[petersalon33 @191072577]

When the altar fire burned for the last time,
the bronze was smashed, burned, and sunk to the riverbed.

Why would a civilization destroy its own faith?

[petersalon33 @191072577]

1200 BC. The East.

The Shang cast bronze to command empires.
The Shu gazed through bulging eyes to speak with gods.
A third force rose from the river valleys.

They fought not for land —
but for who heaven belonged to.

[火山哥🕊️ @huoshan007]

兄弟们以后做视频不需要傻傻的配音了。

自己配嫌麻烦，AI 配音又假，ElevenLabs 这些好用但烧钱，来回调半天人都麻了。

今天给大家一个免费开源狠活：Voicebox。

项目地址：
https://t.co/YetiF0cOVC

它可以复刻声音，做旁白、口播、角色音都能玩。

还能全局语音输入，甚至让 AI Agent 直接开口说话。

最关键：本地运行，不用 API Key，数据不出电脑，想用多少次用多少次。

做内容的人，这玩意儿真有点救命。

配音这块，终于不用每次都像求爷爷告奶奶了。

[探路AI @TanLuAI]

https://t.co/Z1jT53ARmz

[𝗦𝗮𝗻𝗶𝗮 @saniaspeaks_]

GPT image 2 on Chatgpt app.

Prompt

MODERN EDITORIAL COLLAGE POSTER DESIGN. THE BACKGROUND FEATURES FOUR STACKED ROUNDED PANELS FILLED WITH BLACK AND WHITE CINEMATIC PORTRAITS OF A STYLISH YOUNG WOMAN WEARING SUNGLASSES IN DIFFERENT FASHION POSES. OVERLAYED IN THE FOREGROUND IS A HIGH-QUALITY FULL-COLOR CUTOUT OF THE SAME WOMAN WEARING A WHITE OVERSIZED SHIRT WITH BLACK PANTS AND SUNGLASSES, STRIKING A CONFIDENT FASHION POSE.
CLEAN MINIMAL DESIGN, NO TEXT, NO TYPOGRAPHY, NO LETTERS, SOFT SHADOWS, DEPTH LAYERING, HIGH CONTRAST LIGHTING, PREMIUM MAGAZINE STYLE, ULTRA REALISTIC, 8K, PROFESSIONAL POSTER COMPOSITION.

[HiSeven｜🕊️ @hisevenih]

Ai语音圈直接炸锅了。
这个 GitHub 开源黑科技，把 AI 语音做到了离谱的程度，
真正实现了：一句话，一个声音。

记住这个项目名字：VoxCPM2
它在 GitHub 已经拿下了 20K Star。

最夸张的是，
它甚至无需参考音频，
只需要告诉 AI 你的想法，
它就能精准生成你想要的声线。

更狠的是它的语音克隆能力。
只要给它一段音频，
它就能一比一复刻原本的音色、情绪，
甚至连说话节奏都能一起还原。

还原度高达 99%，
几乎听不出差别。

而且不只是日常说话，
连唱歌的声音它都能克隆。
这就真的有点离谱了。

[柳一刀|Reed @Timai9017]

借你的prompt，给太极宗师马老师证明一次😀

[Ai Arainz @iam_mian7]

Ai is taking Things to next level 💥

Cinematic AI Video Prompt :
“Matrix: HARIN vs Smith Clone Army” (15s)

Ultra-realistic IMAX cinematic rooftop fight in heavy rain, Matrix-inspired grey-green cyberpunk tone, wet reflective concrete, glass skyscrapers, stormy atmosphere, 35mm film look, no background music — only natural rain, impacts, debris, and wind sounds.

HARIN: black leather long coat, black fitted outfit, oval sunglasses.
Agent Smith clones: identical black suits, emotionless, hundreds of copies.

Scene opens with HARIN flying violently across the rooftop and crashing into a concrete wall, creating cracks, dust, and rain shockwaves. She slowly stands, adjusts sunglasses, calm and focused.

Rapid montage of hundreds of Smith clones flooding the rooftop through rain and puddles. Rooftop becomes fully covered by the clone army.

Main fight sequence: HARIN launches into ultra-high-speed combat with superhuman martial arts. Flying kicks, spinning attacks, aerial strikes, shockwave punches, bullet-time rain ripples, clones thrown into AC units and off the rooftop. Black lightning motion trails, cinematic motion blur, dynamic aerial camera movement.

The clone army overwhelms her, piling into a massive black-suited human mountain. Rain pounds the surface.

A glowing white energy begins building from inside the mass. Concrete cracks, rainwater reverses upward, pressure intensifies.

HARIN briefly appears through the glowing gap, sunglasses intact, exhales sharply: “하!!”

Massive spherical energy explosion erupts outward, launching clones across the rooftop. Concrete tears apart, rain forms a temporary vacuum sphere before crashing back down.

Final ultra-wide aerial shot: HARIN standing alone calmly in the destroyed rooftop under heavy rain, coat slowly settling, surrounded by storm and skyscrapers.

Constraints:

- Single rooftop environment only
- No blood or gore
- No costume changes
- Sunglasses never break
- No subtitles or text
- No background music
- Total duration: 15 seconds

[Latte @0xbisc]

TENNIS SHOWDOWN

made with GPT Image 2 + Seedance 2 on @openart_ai

Prompt below ↓

[Latte @0xbisc]

Grace Dive

made with GPT Image 2 + Seedance 2
#DreaminaCPP @dreamina_ai

Prompt below ↓

[John @john87445528]

SEEDANCE prompt:

以未经处理的iPhone手持拍摄的真实视频素材风格呈现，所有相机设置均为自动，无任何后期调色或特效。画面带有真实的手持轻微抖动和操作者呼吸感，自动对焦偶尔出现搜索、延迟和短暂失焦，自动白平衡随教室窗户自然光与日光灯混合而在冷暖色调间自然切换。图像整体平坦，保留真实的边缘色差（紫绿 fringes）、轻微过曝或欠曝、运动模糊等光学瑕疵。仅使用画内自然环境音效，无背景音乐，麦克风在强声时可能出现轻微失真。采用学生坐在前排课桌后偷偷第一人称POV中近景仰拍视角，镜头运动为自然反应式而非专业平滑运镜，偶尔因紧张而出现明显抖动和快速调整。中近景构图，女教师上半身在画面中占比极大，胸部以上占据画面大部分空间，脸部和手势细节清晰可见。 接
延长15秒，一位女教师
穿着
hf_20260512_140658_485f11b2-38b1-4076-a9a3-9d38e71616ad
站在讲台上讲心理学课程。她身材丰满，胸部较为丰满突出，气质温和专业，按照用户提供的参考图的发型和服装，无眼镜。表情专注而温和，偶尔微笑，手势自然。她身后是白板和投影屏幕，屏幕上显示着“心理学导论 - 认知偏差”相关内容。教室为普通大学阶梯教室，前排座位上坐着2-3位同学（一位女生低头认真记笔记，一位男生偶尔抬头看老师），他们的头顶和肩膀仅在画面最下方边缘微微可见，形成自然的前景层次。 0秒时，镜头已从中近景位置抬起，女教师胸部以上清晰占据画面大部分空间，按照参考图的发型和服装线条明显，自动对焦稳定在她脸上但仍有轻微手持呼吸抖动，前排同学的头顶仅在画面最下方边缘可见。1秒时，女教师开始讲解，声音清晰富有节奏，镜头因学生轻微调整姿势而出现小幅度晃动，自动对焦在她脸部和手势之间自然切换。2秒时，女教师用手势比划“confirmation bias”，中近景构图让她按照参考图的胸部线条和手部动作都非常清晰，镜头跟随手势轻微上移，带有自然呼吸感。3秒时，女教师转身走向白板写关键词，行走时胸部随着步伐有明显而持续的弹跳，按照参考图的发型和服装在转身后依然自然，镜头反应略慢。4秒时，女教师转回面向学生继续讲解，按照参考图的服装线条在转身后依然明显，镜头保持中近景稳定构图但仍有轻微抖动。5秒时，女教师笑着举例说明，镜头中她的笑容、眼神和按照参考图的丰满胸部线条都非常清晰，自动对焦偶尔因旁边同学轻微移动而短暂失焦又快速恢复。6秒时，女教师的目光突然扫到第一人称的手机镜头，表情从温和转为惊讶，随即浮现出玩味的微笑，镜头因学生紧张而出现明显抖动和快速下沉。7秒时，女教师停止讲解，眼神锁定镜头，带着一丝笑意慢慢走向第一人称，行走时胸部弹跳明显且持续，路过前排同学时，她用眼神淡淡扫过他们，前排同学立刻僵住身体、迅速低下头不敢看她，一位同学手中的笔轻轻掉落，镜头随着她靠近而逐渐拉近，学生紧张的呼吸声明显传入麦克风。8秒时，女教师已经走到第一人称面前，身体微微前倾，近景构图下她的脸和丰满胸部线条清晰可见，她低头用低沉的声音对着镜头说道：“你在拍我？小帅哥，课后到我办公室来一下。”镜头因学生紧张而出现明显抖动，自动对焦短暂失焦后重新拉回。9秒时，女教师保持眼神看着第一人称镜头，嘴角带着一丝玩味的微笑，学生紧张的呼吸声清晰可闻，镜头出现轻微晃动。10秒时，女教师直起身子，嘴角带着一丝笑意看着镜头，镜头仍保持近景。11秒时，女教师转过身慢慢走回讲台，路过前排同学时，他们全部低着头不敢抬头，行走时胸部弹跳依然明显，镜头随着她离开而略微后移，自动对焦跟随她的背影。12秒时，女教师回到讲台继续之前的讲解，表情恢复温和，但嘴角仍带着一丝不易察觉的笑意，镜头保持中近景，学生紧张的呼吸声逐渐平复，自动对焦稳定在她身上。 画面呈现出真实的未经处理手持视频质感，纪录片级别的自然不完美感，无任何后期调色或特效。所有相机行为均符合iPhone自动拍摄的物理特性，带有偷偷拍摄被发现后的紧张感和中近景逐渐拉近的真实比例。

[A.I.Warper @AIWarper]

Below I will teach you how to reverse engineer any 15s video you see

You will need to tweak it a bit but I will explain in this thread exactly how to make these if you are ever curious

Thread below 👇

[serein @sereinworld]

GPT-image2 x seedance2.0

做了一个滑板游戏宣传片的概念

从角色选择、滑板改装、城市地图

到倒计时起跑、空中特技

地铁追逐、屋顶路线

最爽的不是单张图

而是把它串起来之后

真的有点像一款

不存在但很想玩的游戏了

但是还是有一点瑕疵