正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

GPT-Image-2.5 is an impressive step forward. In our evaluations, Flare delivers high-quality images at two to four times the speed of GPT-Image-2. With improved transparent-background generation, it is an excellent fit for creative work on Manus, from brand assets to presentations and websites. Check it out in Manus!

Manus

250,337 subscribers

71,484 次观看 • 13 天前 •via X (Twitter)

艺术科学技术

Anya Rossi• Live Now

Private livecam show

16 条评论

Jason Corkill 的头像

Jason Corkill13 天前

Its not just fast, its also beautiful and accurate!

Justin 的头像

Justin13 天前

Are you utilizing the Astra model and/or Fable 5.1 when utilizing (Manus 1.6 Max)

Sam 的头像

Sam13 天前

Meta deal gets blocked by CCP and now Meta releases @muse with most of @ManusAI’s features

Avi Yadav 的头像

Avi Yadav13 天前

😶 Zuck just acquired Manus AI and created his own version of Manus

nenji55 的头像

nenji5513 天前

まだ使えないようです。早く使ってみたいー

Ferdinand 的头像

Ferdinand13 天前

Manus never disappoints

iksammy1 的头像

iksammy113 天前

Great images

Sebastian Buzdugan 的头像

Sebastian Buzdugan12 天前

saw fast generations pass review then fail from alpha halos on dark backgrounds

Christopher Rizzo 的头像

Christopher Rizzo13 天前

@OpenAIDevs And its cheaper in my experience!

Sebastian Buzdugan 的头像

Sebastian Buzdugan12 天前

transparent backgrounds still need alpha edge checks, halos break brand assets after compositing

AI Mastery Guide 的头像

AI Mastery Guide13 天前

4x faster than GPT-Image-2, nice

م . محمد السلوم 😁 的头像

م . محمد السلوم 😁11 天前

"Love the new features and tools, Manus is truly impressive! However, as a loyal user, I really need help with a critical issue. Between Sept 7–8, my account suffered a massive, unjustified drop of around 10,000 credits. My work has been completely disrupted for days,

Julián H. Ibáñez 的头像

Julián H. Ibáñez11 天前

Que nadie pague por esto. Las infografías que yo hacía por 300 créditos cada una, me las hace ahora por 1500 créditos, encima con errores, edito para que lo subsane y se gasta otros 1500. Osea 3000 en 10 minutos, de los 4000 de la versión pago. ES UN FRAUDE

ze-z 🪐 的头像

ze-z 🪐12 天前

still not available it seems :(

WEEX唯客中文的头像

WEEX唯客中文13 天前

太好用了

Vidya 的头像

Vidya13 天前

@OpenAIDevs Already? You guys are fast!

相关视频

GPT Image 2.5 is now live on OpenArt 🎉 Better images. Better edits. More control over the final result. • Flare Mode for fast creation and iteration • Sunburst Mode for higher-quality generations and precise edits Create from a prompt, edit from a reference, or generate assets with transparent backgrounds.

GPT Image 2.5 is now live on OpenArt 🎉 Better images. Better edits. More control over the final result. • Flare Mode for fast creation and iteration • Sunburst Mode for higher-quality generations and precise edits Create from a prompt, edit from a reference, or generate assets with transparent backgrounds.

OpenArt

23,260 次观看 • 13 天前

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

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

Min Zhou

344,716 次观看 • 5 个月前

Made with GPT Image 2 + Seedance 2.5 on FlovaAI I used the agent but guided it step by step what to use and what to avoid. Skill used: Script to video FlovaAI_Japan #FlovaAI #Flovacpp prompt + Creative inspiration👇

Made with GPT Image 2 + Seedance 2.5 on FlovaAI I used the agent but guided it step by step what to use and what to avoid. Skill used: Script to video FlovaAI_Japan #FlovaAI #Flovacpp prompt + Creative inspiration👇

Sharon Riley

513,465 次观看 • 1 个月前

My canvas based AI image generation tool is live! It's built on top of tldraw and uses Nano Banana 2 Lite for image generation. You can sketch, annotate, collage in a frame... And then click to generate an image. Check it out 👉

My canvas based AI image generation tool is live! It's built on top of tldraw and uses Nano Banana 2 Lite for image generation. You can sketch, annotate, collage in a frame... And then click to generate an image. Check it out 👉

Charlie Clark

50,562 次观看 • 9 个月前

I gave GPT Image 2.5 an iPhone Duo commercial concept instead of asking for one standalone image. The interesting result was the storyboard. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. That means the visual planning stage can connect directly with the rest of the creative workflow. Start with the product idea → build the storyboard → move into video production → refine with AI Edit. If one scene feels off, you can keep working from the same creative direction instead of rebuilding everything. That feels much closer to commercial production than one-shot generation. #GPTImage25 #CapCutPC #AIVideo #Seedance25

I gave GPT Image 2.5 an iPhone Duo commercial concept instead of asking for one standalone image. The interesting result was the storyboard. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. That means the visual planning stage can connect directly with the rest of the creative workflow. Start with the product idea → build the storyboard → move into video production → refine with AI Edit. If one scene feels off, you can keep working from the same creative direction instead of rebuilding everything. That feels much closer to commercial production than one-shot generation. #GPTImage25 #CapCutPC #AIVideo #Seedance25

Kuria | AI

11,843 次观看 • 10 天前

OpenAI's GPT-image-2 is coming to Microsoft Foundry with notable updates for production image workflows: improved editing performance, enhancements to image quality, new multilingual and thinking capabilities, and broader support for resolutions and aspect ratios—including 4K. Together, these updates give teams more flexibility when generating and refining images at scale. Learn more:

OpenAI's GPT-image-2 is coming to Microsoft Foundry with notable updates for production image workflows: improved editing performance, enhancements to image quality, new multilingual and thinking capabilities, and broader support for resolutions and aspect ratios—including 4K. Together, these updates give teams more flexibility when generating and refining images at scale. Learn more:

Microsoft Azure

32,057 次观看 • 5 个月前

GPT-Image-2 was just released... It's the best image model (By a wide margin) Heres how to use GPT-Image-2 in ChatGPT, OpenAI Playground and of Course - Codex. TIMESTAMPS 00:00 Intro 01:27 Initial Tests of GPT-Image-2 02:24 It can GENERATE working BARCODES? 03:40 11 Edits one Prompt 06:40 Creating Cartoons 07:40 Overlay Explanations 08:50 How to Get Started 10:51 IPhone Mockup Images (Amazing) 15:43 Using GPT-Image in OpenAI Playground 16:11 Generate images in 4k 17:44 The FIRST limitation... Its bad at counting 18:26 Using GPT-Image in Codex (Agentic Image Gen)

GPT-Image-2 was just released... It's the best image model (By a wide margin) Heres how to use GPT-Image-2 in ChatGPT, OpenAI Playground and of Course - Codex. TIMESTAMPS 00:00 Intro 01:27 Initial Tests of GPT-Image-2 02:24 It can GENERATE working BARCODES? 03:40 11 Edits one Prompt 06:40 Creating Cartoons 07:40 Overlay Explanations 08:50 How to Get Started 10:51 IPhone Mockup Images (Amazing) 15:43 Using GPT-Image in OpenAI Playground 16:11 Generate images in 4k 17:44 The FIRST limitation... Its bad at counting 18:26 Using GPT-Image in Codex (Agentic Image Gen)

Riley Brown

35,856 次观看 • 5 个月前

New on Poe: Kling 2.0! This advanced video model sets new standards for motion quality and image-to-video capabilities. It excels at transforming images you create on Poe, including those generated with GPT-4o, into high-quality videos. (1/2)

New on Poe: Kling 2.0! This advanced video model sets new standards for motion quality and image-to-video capabilities. It excels at transforming images you create on Poe, including those generated with GPT-4o, into high-quality videos. (1/2)

Poe

15,345 次观看 • 1 年前

GPT-4o Image Generation to Part-based 3D Characters with PBR, in under 10 minutes ⚡️ Workflow: 🎨 Prompt GPT-4o to get an image (e.g., "3D asset of a styled character with all parts laid on a sheet for image to 3D") 🧩 Use CSM AI's Part-based tool to generate parts and assemble in Blender.

GPT-4o Image Generation to Part-based 3D Characters with PBR, in under 10 minutes ⚡️ Workflow: 🎨 Prompt GPT-4o to get an image (e.g., "3D asset of a styled character with all parts laid on a sheet for image to 3D") 🧩 Use CSM AI's Part-based tool to generate parts and assemble in Blender.

Common Sense Machines

442,098 次观看 • 1 年前

GPT Image 2 is rolling out and... Wow. It just one-shot a grid of 100 completely unique pixel art items with meaningful labels in a single image. Prompt in the reply below 👇 More tests with pixel art and Image 2 to come. Follow for more.

GPT Image 2 is rolling out and... Wow. It just one-shot a grid of 100 completely unique pixel art items with meaningful labels in a single image. Prompt in the reply below 👇 More tests with pixel art and Image 2 to come. Follow for more.

proper

194,168 次观看 • 5 个月前

GPT Image 2 is actually insane I made this video with the images from it and it looks so much better than NBP but imo NBP is still way better GPT was a pain in the arse to work with >Constant NSFW tags (on gym pics) >Cant create backgrounds like NBP >Cant swap characters as good as NBP >Less consistent So yeh I’ll be sticking with NBP for now Im going to test making the back grounds and character swaps in NBP then changing them to higher quality with GPT though

GPT Image 2 is actually insane I made this video with the images from it and it looks so much better than NBP but imo NBP is still way better GPT was a pain in the arse to work with >Constant NSFW tags (on gym pics) >Cant create backgrounds like NBP >Cant swap characters as good as NBP >Less consistent So yeh I’ll be sticking with NBP for now Im going to test making the back grounds and character swaps in NBP then changing them to higher quality with GPT though

Pounds

42,082 次观看 • 5 个月前

Qwen‑Image‑2.0 continues to push what’s possible in next‑gen image generation. From pro typography rendering and stronger semantic adherence to improved text rendering and a lighter model, it keeps delivering creative power with ease. Check out the demos to discover more!

Qwen‑Image‑2.0 continues to push what’s possible in next‑gen image generation. From pro typography rendering and stronger semantic adherence to improved text rendering and a lighter model, it keeps delivering creative power with ease. Check out the demos to discover more!

Alibaba Cloud

928,486 次观看 • 6 个月前

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

Peter Gostev

67,245 次观看 • 5 个月前

GPT-5.6 is rolling out in the API. Sol is our flagship model, leading in coding, knowledge work, cybersecurity, and science. Terra delivers performance competitive with GPT-5.5 at lower cost. Luna is our fastest, most affordable model for high-volume tasks.

GPT-5.6 is rolling out in the API. Sol is our flagship model, leading in coding, knowledge work, cybersecurity, and science. Terra delivers performance competitive with GPT-5.5 at lower cost. Luna is our fastest, most affordable model for high-volume tasks.

OpenAI Developers

233,998 次观看 • 2 个月前

This is the kind of AI workflow that makes more sense to me: Don’t try to make the perfect video in one step. Build it. Start with the idea in GPT Image 2.5 and turn it into a visual storyboard. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. Then take the storyboard into CapCut PC’s multi-track timeline and use AI Video with Seedance 2.5 to generate the first full film. Once you have something to work with, use AI Edit to shape it. Generate the foundation. Edit the details. Keep the story. Keep the creative control. Idea → Storyboard → Full Film → Your Version. That feels like a much more sustainable way to make with AI. #GPTImage25 #CapCutPC #AIVideo #Seedance25

This is the kind of AI workflow that makes more sense to me: Don’t try to make the perfect video in one step. Build it. Start with the idea in GPT Image 2.5 and turn it into a visual storyboard. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. Then take the storyboard into CapCut PC’s multi-track timeline and use AI Video with Seedance 2.5 to generate the first full film. Once you have something to work with, use AI Edit to shape it. Generate the foundation. Edit the details. Keep the story. Keep the creative control. Idea → Storyboard → Full Film → Your Version. That feels like a much more sustainable way to make with AI. #GPTImage25 #CapCutPC #AIVideo #Seedance25

Iris Quinn

68,211 次观看 • 10 天前

Qwen‑Image‑2.0 continues to push what’s possible in next‑gen image generation. From pro typography rendering and stronger semantic adherence to improved text rendering and a lighter model architecture, it keeps delivering creative power with ease ✨ Check out the demos to discover more!

Qwen‑Image‑2.0 continues to push what’s possible in next‑gen image generation. From pro typography rendering and stronger semantic adherence to improved text rendering and a lighter model architecture, it keeps delivering creative power with ease ✨ Check out the demos to discover more!

Alibaba Group

3,302,434 次观看 • 6 个月前

I don’t think the goal of AI video should be getting a “perfect” first generation. That’s probably the wrong expectation. For an iPhone Duo commercial, I’d rather: Build the visual direction with GPT Image 2.5 Turn it into video with Seedance 2.5 Then keep editing until the commercial actually works. GPT Image 2.5 is coming to CapCut through existing tools like Design Studio and AI Image, while CapCut PC handles the video workflow and refinement. Generate less blindly Refine more intentionally. #GPTImage25 #CapCutPC #AIVideo #Seedance25

I don’t think the goal of AI video should be getting a “perfect” first generation. That’s probably the wrong expectation. For an iPhone Duo commercial, I’d rather: Build the visual direction with GPT Image 2.5 Turn it into video with Seedance 2.5 Then keep editing until the commercial actually works. GPT Image 2.5 is coming to CapCut through existing tools like Design Studio and AI Image, while CapCut PC handles the video workflow and refinement. Generate less blindly Refine more intentionally. #GPTImage25 #CapCutPC #AIVideo #Seedance25

Iris

127,533 次观看 • 7 天前

MAYBE AI WORKFLOWS WORK BETTER WHEN EVERY MODEL HAS A SPECIFIC JOB. GPT Image 2.5 is coming to CapCut PC through Design Studio and AI Image. Its role? Turn the story into a visual direction. Then CapCut PC's Video Studio takes that direction into production with Seedance 2.5. And once the footage exists, CapCut's AI editing tools take over the refinement. So instead of asking one model to do everything: GPT Image 2.5 → visual thinking Seedance 2.5 → video generation CapCut → editing The result feels less like stacking AI tools and more like building an actual creative pipeline. #GPTImage25 #CapCutPC #AIVideo #Seedance25

MAYBE AI WORKFLOWS WORK BETTER WHEN EVERY MODEL HAS A SPECIFIC JOB. GPT Image 2.5 is coming to CapCut PC through Design Studio and AI Image. Its role? Turn the story into a visual direction. Then CapCut PC's Video Studio takes that direction into production with Seedance 2.5. And once the footage exists, CapCut's AI editing tools take over the refinement. So instead of asking one model to do everything: GPT Image 2.5 → visual thinking Seedance 2.5 → video generation CapCut → editing The result feels less like stacking AI tools and more like building an actual creative pipeline. #GPTImage25 #CapCutPC #AIVideo #Seedance25

Marco | IA

67,893 次观看 • 7 天前

"This is how GPT-4 sees and hears itself" I used GPT-4 to describe itself. Then I used its description to generate an image, a video based on this image and a soundtrack. Tools I used: GPT-4, Midjourney, Kainber AI, Mubert, RunwayML This is the description I used that GPT-4 had of itself as a prompt to text-to-image, image-to-video, and text-to-music. I put the video and sound together in RunwayML.

"This is how GPT-4 sees and hears itself" I used GPT-4 to describe itself. Then I used its description to generate an image, a video based on this image and a soundtrack. Tools I used: GPT-4, Midjourney, Kainber AI, Mubert, RunwayML This is the description I used that GPT-4 had of itself as a prompt to text-to-image, image-to-video, and text-to-music. I put the video and sound together in RunwayML.

Kris Kashtanova

1,233,550 次观看 • 3 年前

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

LMSYS Org

11,216 次观看 • 3 个月前