返回视频列表

OpenAI

Introducing GPT-Image-2.5 in the API

发布
平台
YouTube
时长
1:01
片中语言
美国英语
播放量
30.6万
镜头间隔中位数
3.75s
人脸出镜
63%
暗部画面
0%
OpenAI Introducing GPT-Image-2.5 in the API at 0:00medium presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:00
OpenAI Introducing GPT-Image-2.5 in the API at 0:05close presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:05
OpenAI Introducing GPT-Image-2.5 in the API at 0:07close presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:07
OpenAI Introducing GPT-Image-2.5 in the API at 0:10close presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:10
OpenAI Introducing GPT-Image-2.5 in the API at 0:13close presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:13
OpenAI Introducing GPT-Image-2.5 in the API at 0:14wide presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:14
OpenAI Introducing GPT-Image-2.5 in the API at 0:22
OpenAIIntroducing GPT-Image-2.5 in the API
0:22
OpenAI Introducing GPT-Image-2.5 in the API at 0:28wide presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:28
OpenAI Introducing GPT-Image-2.5 in the API at 0:31medium presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:31
OpenAI Introducing GPT-Image-2.5 in the API at 0:34
OpenAIIntroducing GPT-Image-2.5 in the API
0:34
OpenAI Introducing GPT-Image-2.5 in the API at 0:42
OpenAIIntroducing GPT-Image-2.5 in the API
0:42
OpenAI Introducing GPT-Image-2.5 in the API at 0:43
OpenAIIntroducing GPT-Image-2.5 in the API
0:43
OpenAI Introducing GPT-Image-2.5 in the API at 0:45
OpenAIIntroducing GPT-Image-2.5 in the API
0:45
OpenAI Introducing GPT-Image-2.5 in the API at 0:46
OpenAIIntroducing GPT-Image-2.5 in the API
0:46
OpenAI Introducing GPT-Image-2.5 in the API at 0:48medium presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:48
OpenAI Introducing GPT-Image-2.5 in the API at 0:54close presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:54
OpenAI Introducing GPT-Image-2.5 in the API at 0:55close presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:55
OpenAI Introducing GPT-Image-2.5 in the API at 0:58medium presenter
OpenAIIntroducing GPT-Image-2.5 in the API
0:58
OpenAI Introducing GPT-Image-2.5 in the API at 0:59
OpenAIIntroducing GPT-Image-2.5 in the API
0:59

Introducing GPT-Image-2.5 in the API 的文字记录

由语音模型根据影片自身的音轨转写，并非品牌撰写。点击任意一行即可跳到那一刻。

  1. 0:00Today we're launching two new image generation models, GPT Image 2.5 Sunburst and Flare.
  2. 0:05Sunburst is our most capable model for image generation.
  3. 0:08It brings significant advances in visual fidelity, including sharper detail rendering, more natural lighting, and richer textures.
  4. 0:14With Sunburst, you can bring high-quality visual ideas to life with stronger style and detail.
  5. 0:19You can also refine an idea over multiple edits, like exploring different setups for your dream living room,
  6. 0:24with better preservation of the details you want to keep.
  7. 0:26This model follows detailed instructions more closely, down to which hand someone writes with.
  8. 0:31The second model, Flare, is our fastest image generation model to date.
  9. 0:35It's over 50% faster than GPT-Image 2 while delivering equal quality, so you can explore more ideas faster.
  10. 0:42Both models handle transparent backgrounds, so you can create intricate assets for everything, from infographics to games.
  11. 0:48So, use Sunburst for your most advanced image generation workflows and Flare for quickly generating quality images.
  12. 0:54They're both available now in the API, ChatGPT, and Codex.
  13. 0:58I can't wait to see what you'll build.
13 行 · 179 字

More from OpenAI

All of OpenAI →

The rest of their work we have taken apart.

Introducing Sora, our text-to-video model. Sora can create videos of...Launch98M views
OpenAI
Introducing Sora, our text-to-video model. Sora can create videos of...
0:177 frames0% face
This is GPT-6 Astra. Anything you can do on a computer, Astra can do...30M views
OpenAI
This is GPT-6 Astra. Anything you can do on a computer, Astra can do...
2:43150 frames3.3s cut27% face
Introducing GPT-5.5 A new class of intelligence for real work and po...Launch13M views
OpenAI
Introducing GPT-5.5 A new class of intelligence for real work and po...
0:5522 frames15.4s cut0% face
Introducing ChatGPT Images 2.0 A state-of-the-art image model that c...Launch13M views
OpenAI
Introducing ChatGPT Images 2.0 A state-of-the-art image model that c...
1:0062 frames0.8s cut0% face
ChatGPT already helps millions of people find what to buy. Now it can...Launch10M views
OpenAI
ChatGPT already helps millions of people find what to buy. Now it can...
0:2912 frames0% face

Cut at the same speed

Films whose median shot runs closest to 3.75s.

This weekend we're doubling Composer 2 usage in our new interface. O...Launch232K views
Cursor
This weekend we're doubling Composer 2 usage in our new interface. O...
1:3054 frames3.8s cut63% face
https://t.co/udCpOYBbgj is what we use to ship shaders on Now it's op...72K views
Evil Rabbit
https://t.co/udCpOYBbgj is what we use to ship shaders on Now it's op...
0:5028 frames3.8s cut0% face
This is natural photorealism with Ray3. Every frame feels true to the...53K views
Luma
This is natural photorealism with Ray3. Every frame feels true to the...
0:158 frames3.8s cut0% face
Meta Neural Band's NEW FEATURES Are Finally Here! (Writing on my Leg?! 🤯)Launch10K views
Ray-Ban | Meta
Meta Neural Band's NEW FEATURES Are Finally Here! (Writing on my Leg?! 🤯)
4:02158 frames3.8s cut46% face
Introducing Cursor 3Launch
Cursor
Introducing Cursor 3
1:3054 frames3.8s cut63% face
Shopify Editions | Summer ’25 | TrailerLaunch
Shopify
Shopify Editions | Summer ’25 | Trailer
0:3517 frames3.8s cut6% face
You can now access Box and Dropbox, in addition to Google Drive, OneD...143K views
Perplexity
You can now access Box and Dropbox, in addition to Google Drive, OneD...
0:126 frames3.8s cut0% face
Hey ChatGPT, can you make an invite and presentation for the holiday ...137K views
Figma
Hey ChatGPT, can you make an invite and presentation for the holiday ...
0:5629 frames3.8s cut3% face
How to Enhance Image Quality with Glorify's AI Image UpscalerLaunch227 views
Glorify App
How to Enhance Image Quality with Glorify's AI Image Upscaler
1:4945 frames3.7s cut20% face
The latest technology should be accessible to the elderly, empowering...19K views
Google Gemma
The latest technology should be accessible to the elderly, empowering...
2:58134 frames3.7s cut42% face
TailConverter - Demo video162 views
Guilherme Rizzo
TailConverter - Demo video
0:2614 frames3.8s cut0% face
Cursor can now make to-do lists, search PRs, and queue messages. We’v...526K views
Cursor
Cursor can now make to-do lists, search PRs, and queue messages. We’v...
1:2342 frames3.8s cut38% face

Lit and framed like this

Closest on how much of the running time has a face in it and how dark the frames are.

PetSmart Kitchen featuring IAMS913 views
PetSmart
PetSmart Kitchen featuring IAMS
1:0052 frames1.6s cut63% face
Lift Up, Take Off | Peloton App1.4M views
Peloton
Lift Up, Take Off | Peloton App
0:1519 frames1.2s cut63% face
From idea to sold-out with Base4418M views
Base44
From idea to sold-out with Base44
1:56102 frames1.4s cut64% face
The Digital Double: How Baseten Scaled Its Most-Asked Expert1K views
Notion
The Digital Double: How Baseten Scaled Its Most-Asked Expert
1:3067 frames2.0s cut63% face
Why are you paying for dictation? We're releasing free, unlimited AI...916K views
Willow
Why are you paying for dictation? We're releasing free, unlimited AI...
1:2632 frames29.0s cut63% face
This is you on Ear (3a)17K views
Nothing
This is you on Ear (3a)
0:3245 frames0.6s cut62% face
Attach images and videos to issues and PRs with GitHub CLILaunch3K views
GitHub
Attach images and videos to issues and PRs with GitHub CLI
4:21135 frames14.6s cut61% face
Built on Base443.8M views
Base44
Built on Base44
1:0875 frames1.1s cut64% face
How Indeed Recruit Technologies helps job seekers feel understood with Gemini847 views
Google Workspace
How Indeed Recruit Technologies helps job seekers feel understood with Gemini
3:26171 frames2.8s cut60% face
launching the Amie x Attio integration today!Launch
dennis müller
launching the Amie x Attio integration today!
0:145 frames60% face
Introducing Base44’s Big Game Ad Teaser “It’s App to You”Launch138M views
Base44
Introducing Base44’s Big Game Ad Teaser “It’s App to You”
0:1515 frames1.5s cut67% face
We've put together a short history of how Claude Code came to be, tol...1.1M views
Claude
We've put together a short history of how Claude Code came to be, tol...
0:096 frames6.2s cut67% face

More launch

Same category, other makers, most watched first.

Introducing Base44’s Big Game Ad “It’s App to You”Launch140M views
Base44
Introducing Base44’s Big Game Ad “It’s App to You”
0:3024 frames1.9s cut79% face
Announcing Builder 2.0 We raised $67M to build collaborative coding ...Launch90M views
Steve (Builder.io)
Announcing Builder 2.0 We raised $67M to build collaborative coding ...
0:5218 frames0% face
Introducing Perplexity Computer. Computer unifies every current AI c...Launch38M views
Perplexity
Introducing Perplexity Computer. Computer unifies every current AI c...
1:3432 frames3% face
New Model 3 Performance launching today 🏎️ → 0-60 mph in 2.9 510 hp...Launch34M views
Tesla
New Model 3 Performance launching today 🏎️ → 0-60 mph in 2.9 510 hp...
0:3934 frames0.6s cut3% face
Today we're excited to introduce Devin, the first AI software enginee...Launch31M views
Cognition
Today we're excited to introduce Devin, the first AI software enginee...
1:4937 frames11% face
introducing friend. not imaginary. order now atLaunch27M views
Avi
introducing friend. not imaginary. order now at
1:4450 frames2.9s cut50% face
Introducing Sakana Fugu: A full multi-agent orchestration system acce...Launch26M views
Sakana AI
Introducing Sakana Fugu: A full multi-agent orchestration system acce...
5 frames0% face
Introducing Claude Code Security, now in limited research preview. I...Launch26M views
Claude
Introducing Claude Code Security, now in limited research preview. I...
0:5018 frames0% face
Introducing Gemini Omni: Create Anything from AnythingLaunch26M views
Google
Introducing Gemini Omni: Create Anything from Anything
0:5462 frames0.8s cut8% face
Introducing Code Review, a new feature for Claude Code. When a PR op...Launch24M views
Claude
Introducing Code Review, a new feature for Claude Code. When a PR op...
0:4516 frames6% face
Introducing Claude Managed Agents: everything you need to build and d...Launch22M views
Claude
Introducing Claude Managed Agents: everything you need to build and d...
0:5921 frames0% face
Say goodbye to the silent era of video generation: Introducing Veo 3 ...Launch19M views
Google
Say goodbye to the silent era of video generation: Introducing Veo 3 ...
0:094 frames100% face
Browse every frame in the library