Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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

250,434 subscribers

69,487 views • 5 days ago •via X (Twitter)

Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

16 Comments

Jason Corkill5 days ago

Its not just fast, its also beautiful and accurate!

Justin5 days ago

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

Sam5 days ago

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

Avi Yadav5 days ago

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

nenji555 days ago

まだ使えないようです。早く使ってみたいー

Ferdinand5 days ago

Manus never disappoints

iksammy15 days ago

Great images

Sebastian Buzdugan4 days ago

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

Christopher Rizzo5 days ago

@OpenAIDevs And its cheaper in my experience!

Sebastian Buzdugan4 days ago

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

AI Mastery Guide5 days ago

4x faster than GPT-Image-2, nice

م . محمد السلوم 😁3 days ago

"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. Ibáñez3 days ago

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 🪐4 days ago

still not available it seems :(

WEEX唯客中文5 days ago

太好用了

Vidya5 days ago

@OpenAIDevs Already? You guys are fast!

Related Videos

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

22,662 views • 5 days ago

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

344,268 views • 4 months ago

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 views • 22 days ago

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 views • 9 months ago

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

11,682 views • 1 day ago

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

31,751 views • 4 months ago

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 views • 4 months ago

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 views • 1 year ago

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 views • 1 year ago

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 views • 4 months ago

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 views • 4 months ago

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 views • 5 months ago

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 views • 4 months ago

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 views • 2 months ago

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

68,104 views • 2 days ago

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 views • 5 months ago

"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

1,233,532 views • 3 years ago

🎉 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 views • 2 months ago

gpt-image-2.5 promised richer detail than gpt-image-2 – we verified the setup: two character sheets, each rendered once with gpt-image-2 and once with gpt-image-2.5, animated identically by bytedance's seedance 2.5 observations: • Sam Altman's mouth grille goes from five coarse slots to a fine louvre mesh • sam's wrist gets a brass ring per finger joint and a segmented forearm – image 2 keeps a smooth plate • sam's neck rings stack taller, with visible machined steps • from behind, sam keeps individual hair strands and silver temples – image 2 flattens the back into one mass • Mark Zuckerberg's ringlets separate with visible gaps instead of one denser cap • mark's chain gets real volume and a bevelled-edge pendant • mark's chest emblem glows larger, with light bleeding into the knit around it • from behind, mark's ringlets stay separated all the way round conclusion: every difference above lines up with openai's own claim for images 2.5 – richer textures, more natural lighting, better fidelity to reference detail – on the same two robots, not a new prompt watch the full comparison below 👇

gpt-image-2.5 promised richer detail than gpt-image-2 – we verified the setup: two character sheets, each rendered once with gpt-image-2 and once with gpt-image-2.5, animated identically by bytedance's seedance 2.5 observations: • Sam Altman's mouth grille goes from five coarse slots to a fine louvre mesh • sam's wrist gets a brass ring per finger joint and a segmented forearm – image 2 keeps a smooth plate • sam's neck rings stack taller, with visible machined steps • from behind, sam keeps individual hair strands and silver temples – image 2 flattens the back into one mass • Mark Zuckerberg's ringlets separate with visible gaps instead of one denser cap • mark's chain gets real volume and a bevelled-edge pendant • mark's chest emblem glows larger, with light bleeding into the knit around it • from behind, mark's ringlets stay separated all the way round conclusion: every difference above lines up with openai's own claim for images 2.5 – richer textures, more natural lighting, better fidelity to reference detail – on the same two robots, not a new prompt watch the full comparison below 👇

thehype.

10,189 views • 4 days ago

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,257 views • 1 year ago