ray

[ray @rayidea]

@de3dsoul left

[Jingyuan缘缘 @Jingyuan_521]

Fable 5真的很厉害！我只用一条prompt做了成都市中心3D游览地图，人民公园，安顺廊桥，太古里，宽窄巷子... 本成都人看着都想家了。
prompt：为成都中心城区创建一个 3D 可自由探索的地图 plan.md 文件。设计 plan.md 时，要加入在进入下一步前必须先检查的循环机制。
用@StarchildOnX AI Agent制作

[Jahan Zaib @jzaib4269]

Created with GPT Image 2.0 on ChatGPT

Prompt: Ultra-detailed miniature diorama of China built into the folds of a giant flowing Chinese flag, photographed in a cinematic tilt-shift style. The red silk fabric of the national flag forms rolling hills and valleys across the landscape, with large golden stars visible in the softly blurred background. At the center stands the magnificent blue-roofed Temple of Heaven, surrounded by intricate stone terraces and tiny visitors walking around the monument.
A winding blue river flows through the fabric landscape, crossed by an elegant traditional stone bridge. Small wooden boats glide across the water, creating a lively scene. Around the Temple of Heaven are iconic Beijing landmarks including Tiananmen Gate, the China Central Television (CCTV) Headquarters building, the Beijing Olympic Stadium (Bird’s Nest), the Central Radio & TV Tower, and modern skyscrapers, all rendered as highly detailed miniature architectural models.
Tiny people stroll along pathways illuminated by warm glowing lantern lights, creating a magical atmosphere. The scene combines traditional Chinese culture, modern architecture, tourism, and national pride in one harmonious composition. Shot from a slightly elevated perspective with shallow depth of field, selective focus, realistic textures, soft bokeh, warm golden lighting, ultra-realistic craftsmanship, vibrant red and blue colors, photorealistic miniature world, travel-poster quality, hyper-detailed, 8K resolution, masterpiece, cinematic storytelling, breathtaking visual impact.

[ray @rayidea]

which is better?

[Gadgetify @Gdgtify]

This prompt structure can generate 100s of unique, gorgeous images. I simply asked Ai to pick 4 famous brands and nothing else but food type and other parts can be customized

2x2 grid, do this for 4 famous Fortune 500 brands, 16:9 def plate_dish(): brand_dna = "[$BRAND]" base_dish = "[$FOOD_TYPE, e.g., Deconstructed Cheesecake, Sushi Roll, Macaron]" # Semantic Material Mapping texture_profile = infer_brand_packaging(brand_dna) # e.g., cardboard, glossy plastic, brushed aluminum color_palette = infer_brand_hex_codes(brand_dna) # Culinary Transformation edible_materials = map_to_molecular_gastronomy(texture_profile) # e.g., transforming "matte plastic" into "matte fondant" or "aluminum" into "edible silver leaf" print(f"A hyper-macro food photography shot of a Michelin-star dessert based on {brand_dna}.") print(f"The {base_dish} is constructed using {edible_materials} matching {color_palette}.") print("Lighting: Dramatic restaurant spotlight, black slate plate, smoke/dry ice effects.") print("Garnish: A perfect, delicate sugar-glass rendering of the brand's logo.") execute(plate_dish)

[Marcin @MarcinAI81]

Wow Claude Fable 5 is wild!!

I just told it to make 3 apps with 1 prompt.

1. Jarvis Dashboard
2. Build Apple fitness app
3. Clone my hotel website pixel perfect

results have me speechless

[Int.Lab @IntLab0000]

『魔性』 by InorenA のAIミュージックビデオを公開しました。
アニメ調MV作品なので、今回はあえて、OP風の歌詞付きのバージョンをYoutubeチャンネル上に公開しています。コメント欄にリンクを添えているので、そちらも是非ご覧ください。英訳字幕もあります。

動画生成にはSeedance2.0を使用し、参照画像にはMidjourney v8.1も多用しています。

今回の制作は、tapeheadさん( @tapehead_Lab )が公開されていた、MidjourneyとSeedanceによるコラージュアニメーション技法のnote記事を拝見したのがきっかけでした。
これを自己流にアレンジしてみたところ、作品のタッチを一貫して保ちながらもダイナミックで新鮮な映像表現ができ、新しい可能性を感じました。制作中も、次はどのような映像が生成されるだろうとわくわくするような、自分自身が作品の世界に入り込んで続きが知りたくなるような楽しさがありました。

tapeheadさん、貴重な記事を公開してくださりありがとうございました。
今後は実写風だけではなく、こういったアニメや絵本的なテイストの表現ももっと深掘りしてみようと思います。

[ray @rayidea]

@AdrianPunk115 奈斯

[Adrian Punk @AdrianPunk115]

https://t.co/Q8jdBvx1n3

[ray @rayidea]

@mikefutia SCALE

[Dan Shipper 📧 @danshipper]

BREAKING:

Anthropic just dropped Claude Fable 5—this is Mythos, made safe for public release. It is the best coding model in the world.

We've been testing it internally @every for the last week or so across coding, writing, marketing, editing, and more—here's our vibe check:

- It broke our benchmarks. Fable scored a 91/100 on our Senior Engineer benchmark—this is human senior engineer level. The previous high score was Opus 4.8 at 63. GPT-5.5 is a 62.

- It's a one-shot wonder. You can set it and forget for hours or overnight on huge coding tasks, and come back to completed work. It cleared entire production bug backlogs, built a playable 3D, and even made a 2-minute animated film—all one-shot.

- Taste and attention to detail. In coding and knowledge work tasks, it has much better taste and attention to detail than we've ever seen. It gets subtle things right, adds little features you might not have thought of, and generally understands the assignment in ways that surprised us.

- Great use of context. We set it loose analyzing customer feedback surveys and our website data and it came back with a crisp, clean report that identified a. our biggest problem and b. a concrete testable solution—and then we sent it off to build that.

- It's best for power users. If you're already used to orchestrating multiple agents in your work, this model can do things that you've never seen before. If you're a knowledge worker or vibe coder with a more basic setup, you're not going to notice a huge difference—in fact, it probably isn't the right model for you.

- It's very slow, token-hungry. Using this thing for regular knowledge work is like squashing an ant with a rocket launcher. It also routinely uses 500k to 1M tokens on tasks. That's why it's best for your heaviest jobs—but not as good for tasks like collaborative writing.
- It's expensive. It's about twice as expensive as Opus, and it's also incredibly token hungry—so expect it to be something you'll use sparingly unless your company pays for it.

Overall, I think of it like a warp drive for coding: It can get you across the galaxy in a few hours, when it used to take months or years. But it's not appropriate for getting around town—you need something faster, cheaper, and more maneuverable.

The ceiling is extraordinarily high on this model though. Even our most advanced testers like @kieranklaassen felt like they were only scratching the surface of it.

Want our full vibe check with all of our testing and benchmarks? Read it on @every: https://t.co/MgJLZszJUB

[Adam也叫吉米 @Adam38363368936]

GPT image 2的审美夯到爆，朋友说不敢信这是AI做出的作品😂

今天继续分享高级感的配色：
深海蓝 × 香槟金体系
适合：手表/珠宝/钢笔/豪车/威士忌/游艇

关键词：
奢华、收藏、身份、价值

原因很简单。
深海蓝与金色本来就是珠宝和腕表行业用了几十年的经典组合。
AI只是把这种关系重新放大了。

提示词👇

[Mnimiy @Mnilax]

https://t.co/XpGXVjbkup

[Josh Daws @JoshDaws]

Claude Fable just built this entire product from one prompt. I'm blown away.

Shotblock is a 3D shot-planning tool for AI filmmakers — real lens math, actor blocking, 180 ° rule warnings, animatics, storyboard + prompt export. It researched storyboard conventions, wrote its own test suite, verified everything in a browser, and deployed it.

Then I asked for a promo video. It scripted, recorded, and edited the one below with minimal direction.

Give it a try. Free, no signup. Feedback button in the app for any issues or feature requests.

https://t.co/EEx9ClAC9m

[Kailash @kail_designs]

Made this video in 5 prompts 😉

[ray @rayidea]

图像放大之神https://t.co/b63pZ3rX3s

[ray @rayidea]

@zhangcw04 碌鸠？

[ray @rayidea]

@RevvCulture Lynk & Co represents the forefront of Chinese automotive industry design

[ray @rayidea]

@gregisenberg Will driving this car really not be distracting?

[ray @rayidea]

@kimzooh 광동 요리에는 아직 발견해야 할 놀라움이 정말 많아요.