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。

We gave four frontier image editing models the same photo and 30 edits in a row: Ideogram 4.5 keeps most of the room intact, while the others drift, GPT Image 2.5 Sunburst most visibly. We've seen some interesting demos of multi-turn editing consistency from the latest image editing models,... so we ran our own test: GPT Image 2.5 Sunburst, #1 on our Image Editing leaderboard, against Ideogram 4.5, FLUX 3 and Nano Banana 2.1. Our leaderboard scores single edits; this tests what happens when 30 consecutive changes stack up, with each model editing its own previous output through a 30-step real estate staging sequence: light the fire, add a sofa, repaint the walls, swap day for twilight, and more. Why are the final results so different? Ideogram's Ideogram 4.5 and BlackForestLabsAI - Unofficial's FLUX 3 edit locally. On small edits like adding a vase of tulips, we measured that they left 95% or more of the image essentially untouched. GPT Image 2.5 (Sunburst) re-renders most of the entire image on every edit, leaving only about a fifth of the image unchanged, so small shifts in colour and detail compound over turns. Nano Banana 2.1 sits in between: its edits stay local, but the rest of the image shifts slightly and gradually darkens.show more

Artificial Analysis

157,099 subscribers

52,850 次观看 • 1 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

serx · fireply.ai 的头像

serx · fireply.ai1 天前

95% untouched on a tulip vase edit is the number i care about

Som Dutt | AI/ML Analyst 的头像

Som Dutt | AI/ML Analyst1 天前

Best single edit ≠ best editor. Once edits stack, pixel preservation beats raw quality. Would love to see “% unchanged per edit” tracked on the leaderboard itself.

aqui 的头像

aqui1 天前

funny how they marketed Image 2.5 as the most consistent editing model

Tatsuya 的头像

Tatsuya1 天前

ideogram winning this is the surprise, nobody talks about them

Simo | ai-costguard 的头像

Simo | ai-costguard1 天前

Each edit looks fine. The sequence is where it falls apart

Wei佳的头像

Wei佳1 天前

Ideogram editing locally while GPT re-renders everything each turn. That's your drift, right there.

Mehmed II 的头像

Mehmed II1 天前

so ideogram ftw GPT image has always been shite for consistency across edits

Lover of Apps 的头像

Lover of Apps1 天前

I already put Ideogram 4.5 in my workflow for edits.

Rakesh Sahni 的头像

Rakesh Sahni1 天前

"add tulips" shouldn't mean "change the whole room." the 95% vs roughly 20% gap is striking. i'd like to know what "unchanged" means here: - identical pixels - OR are tiny colour shifts allowed? that cutoff matters when reading those numbers.

相关视频

Ideogram 4.5 is now in ComfyUI. It's an edit model built to fix drift. 4.5 keeps the rest of your image intact, edit after edit. → Multi-turn edits that stay clean → Edit 24MP+ images without downscaling, with crop edges preserved so the edit stitches back in seamlessly → Translate text in signage, packaging, and banners → Style reference, sketch-to-image, depth-to-image, and photo restoration Click the link below to run the workflows ⬇️

Ideogram 4.5 is now in ComfyUI. It's an edit model built to fix drift. 4.5 keeps the rest of your image intact, edit after edit. → Multi-turn edits that stay clean → Edit 24MP+ images without downscaling, with crop edges preserved so the edit stitches back in seamlessly → Translate text in signage, packaging, and banners → Style reference, sketch-to-image, depth-to-image, and photo restoration Click the link below to run the workflows ⬇️

ComfyUI

27,357 次观看 • 10 天前

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 次观看 • 2 年前

Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2.1 by Qwen up to 6.3× faster for image generation and editing. - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance. - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? The 8-step adapter is our recommended default. It supports text-to-image and single- or multi-image editing at 1K resolution, with up to three reference images. - 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸?The LoRA adapters load directly on top of Qwen-Image-2.1, while the pipeline remains unchanged. Each adapter uses its own optimized sigma schedule and runs without CFG. 𝘛𝘩𝘪𝘴 𝘪𝘴 𝘫𝘶𝘴𝘵 𝘰𝘶𝘳 𝘧𝘪𝘳𝘴𝘵 𝘳𝘦𝘭𝘦𝘢𝘴𝘦, 𝘸𝘪𝘵𝘩 𝘦𝘷𝘦𝘯 𝘣𝘦𝘵𝘵𝘦𝘳 𝘷𝘦𝘳𝘴𝘪𝘰𝘯𝘴 𝘰𝘯 𝘵𝘩𝘦 𝘸𝘢𝘺. 🚀 Want to try the fast open-source integration? Check it here on Diffusers: Want to try the fastest image generation and editing endpoint? Check P-Image-Ideogram and P-Image-Edit here on API:

Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2.1 by Qwen up to 6.3× faster for image generation and editing. - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance. - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? The 8-step adapter is our recommended default. It supports text-to-image and single- or multi-image editing at 1K resolution, with up to three reference images. - 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸?The LoRA adapters load directly on top of Qwen-Image-2.1, while the pipeline remains unchanged. Each adapter uses its own optimized sigma schedule and runs without CFG. 𝘛𝘩𝘪𝘴 𝘪𝘴 𝘫𝘶𝘴𝘵 𝘰𝘶𝘳 𝘧𝘪𝘳𝘴𝘵 𝘳𝘦𝘭𝘦𝘢𝘴𝘦, 𝘸𝘪𝘵𝘩 𝘦𝘷𝘦𝘯 𝘣𝘦𝘵𝘵𝘦𝘳 𝘷𝘦𝘳𝘴𝘪𝘰𝘯𝘴 𝘰𝘯 𝘵𝘩𝘦 𝘸𝘢𝘺. 🚀 Want to try the fast open-source integration? Check it here on Diffusers: Want to try the fastest image generation and editing endpoint? Check P-Image-Ideogram and P-Image-Edit here on API:

Pruna AI

90,322 次观看 • 16 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 • 26 天前

Nano Banana is now live in Search, so you can use Lens & AI Mode to instantly transform photos with our latest image editing model. Here’s a guide to get you started: 1. Open Lens in the Google app for Android and iOS. 2. Tap the new Create mode — look for the yellow banana 🍌 3. Try a suggested prompt, like “make a photo booth pic of me.” 4. Or, snap a picture and describe the edits you’re looking for. 5. Use follow-ups to keep editing, or share the image with family and friends.

Nano Banana is now live in Search, so you can use Lens & AI Mode to instantly transform photos with our latest image editing model. Here’s a guide to get you started: 1. Open Lens in the Google app for Android and iOS. 2. Tap the new Create mode — look for the yellow banana 🍌 3. Try a suggested prompt, like “make a photo booth pic of me.” 4. Or, snap a picture and describe the edits you’re looking for. 5. Use follow-ups to keep editing, or share the image with family and friends.

Google

221,030 次观看 • 11 个月前

InstantDrag Improving Interactivity in Drag-based Image Editing discuss: Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately reflecting user interaction while maintaining image content. Some existing approaches rely on computationally intensive per-image optimization or intricate guidance-based methods, requiring additional inputs such as masks for movable regions and text prompts, thereby compromising the interactivity of the editing process. We introduce InstantDrag, an optimization-free pipeline that enhances interactivity and speed, requiring only an image and a drag instruction as input. InstantDrag consists of two carefully designed networks: a drag-conditioned optical flow generator (FlowGen) and an optical flow-conditioned diffusion model (FlowDiffusion). InstantDrag learns motion dynamics for drag-based image editing in real-world video datasets by decomposing the task into motion generation and motion-conditioned image generation. We demonstrate InstantDrag's capability to perform fast, photo-realistic edits without masks or text prompts through experiments on facial video datasets and general scenes. These results highlight the efficiency of our approach in handling drag-based image editing, making it a promising solution for interactive, real-time applications.

InstantDrag Improving Interactivity in Drag-based Image Editing discuss: Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately reflecting user interaction while maintaining image content. Some existing approaches rely on computationally intensive per-image optimization or intricate guidance-based methods, requiring additional inputs such as masks for movable regions and text prompts, thereby compromising the interactivity of the editing process. We introduce InstantDrag, an optimization-free pipeline that enhances interactivity and speed, requiring only an image and a drag instruction as input. InstantDrag consists of two carefully designed networks: a drag-conditioned optical flow generator (FlowGen) and an optical flow-conditioned diffusion model (FlowDiffusion). InstantDrag learns motion dynamics for drag-based image editing in real-world video datasets by decomposing the task into motion generation and motion-conditioned image generation. We demonstrate InstantDrag's capability to perform fast, photo-realistic edits without masks or text prompts through experiments on facial video datasets and general scenes. These results highlight the efficiency of our approach in handling drag-based image editing, making it a promising solution for interactive, real-time applications.

AK

71,232 次观看 • 2 年前

Google Pics — our image creation and editing tool in Google Workspace — is rolling out to Google AI Pro and Ultra subscribers and most Workspace business customers. Built on our Nano Banana image generation and editing model, Pics gives you the control you need to create whatever you're imagining — like designing a poster, producing social media posts, or editing digital illustrations. It also includes a suite of fine-tuned editing capabilities that let you generate images and make precise edits rather than starting from scratch.

Google Pics — our image creation and editing tool in Google Workspace — is rolling out to Google AI Pro and Ultra subscribers and most Workspace business customers. Built on our Nano Banana image generation and editing model, Pics gives you the control you need to create whatever you're imagining — like designing a poster, producing social media posts, or editing digital illustrations. It also includes a suite of fine-tuned editing capabilities that let you generate images and make precise edits rather than starting from scratch.

Google

249,506 次观看 • 1 个月前

OpenAI launched GPT‑Image‑2.5 Sunburst a few days ago. We stress-tested it's object-swap capabilities using the the invideo editor to create this cool match-cut video. Why? The biggest unlock with Sunburst is that when you edit images - NOTHING except the item you're swapping changes in your frame. Most models before this would do a good job editing images, but the rest of the frame changed ever so slightly. With 2.5 Sunburst, that doesn't happen anymore. Combine that with an agent building your timeline and lining up your edited images for that perfect match cut feel - without you having to manually line-up, cut, and re-insert edited images on the timeline at the exact right spot, is where the biggest unlock is. We created this in a few hours, with our in-house creator directing the idea and an invideo editing agent building and polishing the timeline.

OpenAI launched GPT‑Image‑2.5 Sunburst a few days ago. We stress-tested it's object-swap capabilities using the the invideo editor to create this cool match-cut video. Why? The biggest unlock with Sunburst is that when you edit images - NOTHING except the item you're swapping changes in your frame. Most models before this would do a good job editing images, but the rest of the frame changed ever so slightly. With 2.5 Sunburst, that doesn't happen anymore. Combine that with an agent building your timeline and lining up your edited images for that perfect match cut feel - without you having to manually line-up, cut, and re-insert edited images on the timeline at the exact right spot, is where the biggest unlock is. We created this in a few hours, with our in-house creator directing the idea and an invideo editing agent building and polishing the timeline.

Invideo

201,146 次观看 • 29 天前

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 次观看 • 1 个月前

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

AK

143,469 次观看 • 3 年前

Announcing Gemini 2.5 Flash Image! (Nano Banana) from Google DeepMind. This model brings you state of the art image generation! Here's 7m of demos. Today marks a leap forward in AI-powered image creativity with the launch of stronger native image generation and editing in Gemini 2.5 Flash. Here's what's new: 👤 Consistent character design: Maintain a character's identity across multiple images, changing their outfits, poses, and scenes without losing their core look. 🎨 Creative composition: Seamlessly merge elements from up to three different images into a single, cohesive masterpiece. The potential for surrealist art and unique compositions is endless. ✍️ Targeted edits with natural language: Go beyond the prompt. You can now make highly specific edits like "change the background," "restore this faded photo," or "edit the character's outfit" with simple commands. ✨ Design & identity adaptation: Apply a specific style, texture, or pattern from one image to another, unlocking new possibilities for fashion, product design, and architectural visualization. I've put together a ~7-minute video demo to walk you through these features and show just how powerful they are in action. We can't wait to see what you all create! Try the model out in Google AI Studio, Gemini app or the Gemini API.

Announcing Gemini 2.5 Flash Image! (Nano Banana) from Google DeepMind. This model brings you state of the art image generation! Here's 7m of demos. Today marks a leap forward in AI-powered image creativity with the launch of stronger native image generation and editing in Gemini 2.5 Flash. Here's what's new: 👤 Consistent character design: Maintain a character's identity across multiple images, changing their outfits, poses, and scenes without losing their core look. 🎨 Creative composition: Seamlessly merge elements from up to three different images into a single, cohesive masterpiece. The potential for surrealist art and unique compositions is endless. ✍️ Targeted edits with natural language: Go beyond the prompt. You can now make highly specific edits like "change the background," "restore this faded photo," or "edit the character's outfit" with simple commands. ✨ Design & identity adaptation: Apply a specific style, texture, or pattern from one image to another, unlocking new possibilities for fashion, product design, and architectural visualization. I've put together a ~7-minute video demo to walk you through these features and show just how powerful they are in action. We can't wait to see what you all create! Try the model out in Google AI Studio, Gemini app or the Gemini API.

Addy Osmani

159,264 次观看 • 1 年前

Seedance 2.0 - Advanced Workflows Series 11. Cinematic Camera Angles through Video Gen + Specialized Storyboard AI Agent Are you already getting camera shots and angles through Nano Banana Pro? Take the next step. Seedance 2.0 has a better spatial understanding of the scene than image generation models. Because it is built to produce cinematic clips, it achieves more beautiful shots and angles than image models like Nano Banana, which are primarily made for image editing. As an added bonus, Seedance renders the entire space of the scene, so you can get tens of shots with complete spatial and element consistency in a single generation. Create a specific AI Agent to help you with storyboarding, and feed the input into Seedance to get the most cinematic shots. You can access Seedance 2.0 now on insMind (link at the end of the thread). Workflow + Prompts👇

Seedance 2.0 - Advanced Workflows Series 11. Cinematic Camera Angles through Video Gen + Specialized Storyboard AI Agent Are you already getting camera shots and angles through Nano Banana Pro? Take the next step. Seedance 2.0 has a better spatial understanding of the scene than image generation models. Because it is built to produce cinematic clips, it achieves more beautiful shots and angles than image models like Nano Banana, which are primarily made for image editing. As an added bonus, Seedance renders the entire space of the scene, so you can get tens of shots with complete spatial and element consistency in a single generation. Create a specific AI Agent to help you with storyboarding, and feed the input into Seedance to get the most cinematic shots. You can access Seedance 2.0 now on insMind (link at the end of the thread). Workflow + Prompts👇

VoxelPlot

126,565 次观看 • 5 个月前

There’s a difference between regenerating a video and actually editing one. Regeneration asks: “What if I try again?” Editing asks: “What exactly should change?” That’s why this workflow makes sense to me. GPT Image 2.5 is coming to CapCut, available through Design Studio and AI Image. Start by turning the idea into a visual storyboard. Then use AI Video with Seedance 2.5 in CapCut PC’s multi-track timeline to generate the full video. Once you have footage, AI Edit lets you make targeted changes instead of throwing away the entire result. The more AI video improves, the more important that distinction becomes. Generation creates possibilities. Editing creates decisions. #GPTImage25 #CapCutPC #AIVideo #Seedance25

There’s a difference between regenerating a video and actually editing one. Regeneration asks: “What if I try again?” Editing asks: “What exactly should change?” That’s why this workflow makes sense to me. GPT Image 2.5 is coming to CapCut, available through Design Studio and AI Image. Start by turning the idea into a visual storyboard. Then use AI Video with Seedance 2.5 in CapCut PC’s multi-track timeline to generate the full video. Once you have footage, AI Edit lets you make targeted changes instead of throwing away the entire result. The more AI video improves, the more important that distinction becomes. Generation creates possibilities. Editing creates decisions. #GPTImage25 #CapCutPC #AIVideo #Seedance25

Grand AI Hub

99,228 次观看 • 29 天前

Meta just launched its 1st image model after Mark Zuckerberg’s AI shake-up. Muse Image is Meta Superintelligence Labs' first image generator after Muse Spark. They said the model will power new editing features in Meta’s Instagram photo app and be added to its marketer tools for creating platform ads. Meta had relied on Midjourney and Black Forest Labs for generation inside Meta AI. Muse Image brings that layer in-house, so Meta controls quality, cost, and product timing. Consumers get free access through Meta AI, WhatsApp chats, and Instagram Stories. Power users need Meta One or another monthly plan when free limits run out. Users can start from prompts, add photos, annotate edits, or sketch changes directly. Meta says it can erase photobombers, create QR codes, and keep visual text readable. Advertisers get variants through Advantage+ creative, with edits, style swaps, and brand-matched versions. Meta says internal tests trail GPT Image 2 but beat Nano Banana 2 on editing. This is another move in Meta's effort in trying to convert AI infrastructure spending into revenue beyond social ads.

Rohan Paul

20,377 次观看 • 3 个月前

Learn about Google’s new SOTA image model, Gemini 2.5 Flash, its key capabilities, and what’s next on the roadmap with some of the team behind the model Nicole Brichtova Kaushik Shivakumar Mostafa Dehghani Robert Riachi with Logan Kilpatrick. Timecodes: 0:37 New model introduction 01:21 Demo: Image editing 03:44 Text rendering capabilities 04:44 Beyond human preference evals 06:44 Text rendering as a proxy for quality 08:38 Positive transfer between modalities 11:25 Demo: multi-turn, context aware image generation 13:54 Pixel-perfect editing and character consistency 15:51 Interleaved image generation 17:59 Specialized vs. native models 19:52 Understanding nuanced prompts 20:59 User feedback shaping model development 22:37 Improvements in character consistency 24:17 More natural looking images from team collaboration 26:41 What’s next for image generation models

Learn about Google’s new SOTA image model, Gemini 2.5 Flash, its key capabilities, and what’s next on the roadmap with some of the team behind the model Nicole Brichtova Kaushik Shivakumar Mostafa Dehghani Robert Riachi with Logan Kilpatrick. Timecodes: 0:37 New model introduction 01:21 Demo: Image editing 03:44 Text rendering capabilities 04:44 Beyond human preference evals 06:44 Text rendering as a proxy for quality 08:38 Positive transfer between modalities 11:25 Demo: multi-turn, context aware image generation 13:54 Pixel-perfect editing and character consistency 15:51 Interleaved image generation 17:59 Specialized vs. native models 19:52 Understanding nuanced prompts 20:59 User feedback shaping model development 22:37 Improvements in character consistency 24:17 More natural looking images from team collaboration 26:41 What’s next for image generation models

Google AI Developers

31,742 次观看 • 1 年前

This is the craziest model you'll see this week! This model powers Figma. It's also behind Wayfair and a bunch of major e-commerce retailers. This model is a PIXEL-PERFECT image editing model. Literally, "pixel perfect". The model is capable of modifying one image while keeping everything else untouched. It's a model designed, developed, and deployed by the research team at Jasper. This beats OpenAI models, Nano Banana, and every single general image model I've seen so far. It's up to 100x less expensive to run, and up to 10X faster. I recorded a quick video to show you how impressive this is. There's a ton of research behind this model. I'm adding two links below so you can read about how this model works, specifically about "Latent Bridge Matching" and "Flash Diffusion".

This is the craziest model you'll see this week! This model powers Figma. It's also behind Wayfair and a bunch of major e-commerce retailers. This model is a PIXEL-PERFECT image editing model. Literally, "pixel perfect". The model is capable of modifying one image while keeping everything else untouched. It's a model designed, developed, and deployed by the research team at Jasper. This beats OpenAI models, Nano Banana, and every single general image model I've seen so far. It's up to 100x less expensive to run, and up to 10X faster. I recorded a quick video to show you how impressive this is. There's a ton of research behind this model. I'm adding two links below so you can read about how this model works, specifically about "Latent Bridge Matching" and "Flash Diffusion".

Santiago

25,886 次观看 • 11 个月前

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

89,392 次观看 • 1 年前

Today, we introduce HunyuanImage 3.0-Instruct, a native multimodal model focusing on image-editing by integrating visual understanding with precise image synthesis! 🚀 It understands input images and reasons before generating images. Built on an 80B-parameter MoE architecture (13B activated), it natively unifies deep multimodal comprehension and high-fidelity generation. 🧠 A "Thinking" Model with Native CoT & MixGRPO: The model doesn’t just execute commands, it processes them through a Native Chain-of-Thought (CoT) schema. Enhanced by our self-developed MixGRPO algorithm, it reasons through complex instructions to achieve flawless intent alignment and human-preference consistency. 🎨 Precise Editing & Multi-Image Fusion: The model enables accurate image editing by adding, removing, or modifying elements while keeping non-target areas perfectly intact. It also excels at seamless multi-image fusion, synthesizing complex scenes by extracting and blending elements from multiple sources into a unified, consistent output. 🏆 SOTA Performance: HunyuanImage 3.0-Instruct sets a new benchmark in visual quality and alignment, delivering performance that matches leading proprietary models. We aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant image generation ecosystem. 🛠️🎨 💻Try it at (PC only):

Today, we introduce HunyuanImage 3.0-Instruct, a native multimodal model focusing on image-editing by integrating visual understanding with precise image synthesis! 🚀 It understands input images and reasons before generating images. Built on an 80B-parameter MoE architecture (13B activated), it natively unifies deep multimodal comprehension and high-fidelity generation. 🧠 A "Thinking" Model with Native CoT & MixGRPO: The model doesn’t just execute commands, it processes them through a Native Chain-of-Thought (CoT) schema. Enhanced by our self-developed MixGRPO algorithm, it reasons through complex instructions to achieve flawless intent alignment and human-preference consistency. 🎨 Precise Editing & Multi-Image Fusion: The model enables accurate image editing by adding, removing, or modifying elements while keeping non-target areas perfectly intact. It also excels at seamless multi-image fusion, synthesizing complex scenes by extracting and blending elements from multiple sources into a unified, consistent output. 🏆 SOTA Performance: HunyuanImage 3.0-Instruct sets a new benchmark in visual quality and alignment, delivering performance that matches leading proprietary models. We aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant image generation ecosystem. 🛠️🎨 💻Try it at (PC only):

Tencent Hy

126,668 次观看 • 8 个月前

Google DeepMind Developers: How Nano Banana Was Made In this episode, we sat down with Google DeepMind’s Oliver Wang and Nicole Brichtova to discuss how Nano Banana was created, why it became so viral, and what’s in store for the future of image and video editing. 00:00 Intro 02:00 The origin of Nano Banana 06:20 Seeing yourself in AI 11:00 Control & character consistency 17:10 AI in education and visual learning 24:10 2D vs 3D: Debate over world models 31:10 The Japan phenomenon 35:00 From images to video 41:00 Working with artists 47:30 The next era of image models 53:50 Closing thoughts Oliver Wang Nicole Brichtova Guido Appenzeller Yoko

Google DeepMind Developers: How Nano Banana Was Made In this episode, we sat down with Google DeepMind’s Oliver Wang and Nicole Brichtova to discuss how Nano Banana was created, why it became so viral, and what’s in store for the future of image and video editing. 00:00 Intro 02:00 The origin of Nano Banana 06:20 Seeing yourself in AI 11:00 Control & character consistency 17:10 AI in education and visual learning 24:10 2D vs 3D: Debate over world models 31:10 The Japan phenomenon 35:00 From images to video 41:00 Working with artists 47:30 The next era of image models 53:50 Closing thoughts Oliver Wang Nicole Brichtova Guido Appenzeller Yoko

a16z

97,860 次观看 • 11 个月前