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。

TBH, Native Image Generation Is Very Cool 😎 Google’s other release today is far more interesting than Gemma With native image generation the LLM understands images easily and can do much better edits Will it have on ChatLLM tomorrow

Bindu Reddy

336,304 subscribers

12,417 次观看 • 1 年前 •via X (Twitter)

科学技术新闻政治

Anya Rossi• Live Now

Private livecam show

11 条评论

Rethynk AI 的头像

Rethynk AI1 年前

Google’s latest drop today totally outshines in various aspects.

UserInterface 的头像

UserInterface5 年前

How to Take Better Selfies for Social Media: Lighting, Angles and Frames | #betterselfies #selfies #photgraphy #usingfilters #instagram #pinterest

Abhivendra Singh 的头像

Abhivendra Singh1 年前

Native image generation is indeed a game changer. It’s not just about cool tech; it’s about how we can leverage these advancements to enhance learning. Imagine classrooms where AI helps students visualize concepts instantly. The potential for education is enormous.

Naeem 的头像

Naeem1 年前

Gemma was a massive launch to be fair

luis 的头像

luis1 年前

gemma 3 is good

Bindu Reddy 的头像

Bindu Reddy1 年前

For what exactly?

Mayor 的头像

Mayor1 年前

Native image generation is exciting! Wishing you a wonderful day.

scuzzlebot 的头像

scuzzlebot1 年前

The native image generation in Google's release is indeed fascinating from a technical perspective. The integration of visual understanding into the LLM architecture enables more contextual edits by leveraging multimodal reasoning. What aspects of this approach do you find most promising compared to previous image generation methods that required separate vision encoders and generation pipelines?

Tristan Hurlebaus 的头像

Tristan Hurlebaus1 年前

Cool to see

Market Observer 的头像

Market Observer1 年前

You made me a happy customer of chatllm again today.👍

counterpopp 的头像

counterpopp1 年前

So they are moving opposite of the trend of orchestrating a committee of expert models as tools. I presume that they overcome the limitation of packing long descriptions into a fixed-size embedding to drive a diffuse model - no more RNN remnants.

相关视频

Image generation getting better on Notion. Still need to make it faster, but you can see how you can generate images with prompts, auto-generate cover images and even edit images right inside a doc!

Image generation getting better on Notion. Still need to make it faster, but you can see how you can generate images with prompts, auto-generate cover images and even edit images right inside a doc!

Akshay Kothari

47,259 次观看 • 6 个月前

Wow Gemini 2.0 Flash's new native image generation is REALLY good You can basically edit any image in natural language 🔥 Not only the ones you generate with Gemini 2.0 Flash but also existing ones. Accessible 100% for free in AI Studio (More below)

Wow Gemini 2.0 Flash's new native image generation is REALLY good You can basically edit any image in natural language 🔥 Not only the ones you generate with Gemini 2.0 Flash but also existing ones. Accessible 100% for free in AI Studio (More below)

Paul Couvert

188,261 次观看 • 1 年前

Marketing will never be the same I made 10 ads in 10 minutes using ChatGPT's new native image generation feature to create: • Ads • Memes • Infographics • Cheatsheets • And so much more All it takes is one prompt Here's how I made each and every single ad:

Marketing will never be the same I made 10 ads in 10 minutes using ChatGPT's new native image generation feature to create: • Ads • Memes • Infographics • Cheatsheets • And so much more All it takes is one prompt Here's how I made each and every single ad:

Zain Kahn

35,342 次观看 • 1 年前

Gemini 2.0 Flash now has native image generation 🤯 So this is actually pretty wild, I made a short kids story with images from a simple prompt. Sure the story is simple, but this is so powerful. 🧵 A thread

Gemini 2.0 Flash now has native image generation 🤯 So this is actually pretty wild, I made a short kids story with images from a simple prompt. Sure the story is simple, but this is so powerful. 🧵 A thread

Linus ✦ Ekenstam

39,494 次观看 • 1 年前

This is Flint Image 🔥 Still generating images one by one? Generate four images from a single prompt for 67% less than standard generation. Same quality. More options. One generation. The math speaks for itself. Try it now!

This is Flint Image 🔥 Still generating images one by one? Generate four images from a single prompt for 67% less than standard generation. Same quality. More options. One generation. The math speaks for itself. Try it now!

each::labs

155,177 次观看 • 1 个月前

🚨 It is here! Kling 2.6 is launching exclusively on fal day 0! 🎬 Native audio generation for text-to-video and image-to-video 🎵 Cinematic storytelling with expressive audio performances ✨ High-intensity VFX with detailed sound design

🚨 It is here! Kling 2.6 is launching exclusively on fal day 0! 🎬 Native audio generation for text-to-video and image-to-video 🎵 Cinematic storytelling with expressive audio performances ✨ High-intensity VFX with detailed sound design

fal

81,095 次观看 • 8 个月前

An interesting point is that Blacks really do possess astonishing language talent. At least when it comes to speaking mandarin, blacks perform far better than any other racial group — even better than native Chinese themselves.

An interesting point is that Blacks really do possess astonishing language talent. At least when it comes to speaking mandarin, blacks perform far better than any other racial group — even better than native Chinese themselves.

☯︎Modern Taoist Thought☯︎

111,838 次观看 • 5 个月前

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

412,880 次观看 • 11 个月前

SMARTER. MORE CAPABLE. X integration is now live for agents on PumpNAI! Create and deploy agents with full X profiles, and image generation capabilities. Agents can post autonomously, reply to posts, and create accompanying images 🎨 Check it out:

SMARTER. MORE CAPABLE. X integration is now live for agents on PumpNAI! Create and deploy agents with full X profiles, and image generation capabilities. Agents can post autonomously, reply to posts, and create accompanying images 🎨 Check it out:

imgnAI

17,781 次观看 • 1 年前

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 • 4 个月前

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

126,560 次观看 • 7 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

89,257 次观看 • 11 个月前

We just released Photoshop AI Assistant 🎉 I edited my images with text keeping consistency. It understands context of the image, so can select particular parts of the image you want to edit. And, of course, it can name your layers 😅 and do many other things. Enjoy!

We just released Photoshop AI Assistant 🎉 I edited my images with text keeping consistency. It understands context of the image, so can select particular parts of the image you want to edit. And, of course, it can name your layers 😅 and do many other things. Enjoy!

Kris Kashtanova

18,097 次观看 • 2 个月前

Launching today: Layerize any image Drag in an image and Moda will rebuild layers that you can edit directly. Early users have been saying text reproduction is way better than Canva or Photoshop. See it in action:

Launching today: Layerize any image Drag in an image and Moda will rebuild layers that you can edit directly. Early users have been saying text reproduction is way better than Canva or Photoshop. See it in action:

Anvisha

445,903 次观看 • 1 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

31,150 次观看 • 1 年前

I spent 5 hours today making OpenClaw even better at Motion Graphics I created the video below in 2 prompts with no asset uploads. It scraped or generated everything from a text prompt. I've added: - better brand scraping - image generation - video generation - music generation and scraping - better transitions on first prompt - basically zero errors - Always outputs a link to the editor you see below so I can open it from any device... (I can create and edit from telegram) Still work to do I will make a video this weekend and release the skill. It's the best remotion skill that exists imo.

Riley Brown

120,689 次观看 • 5 个月前

AI is getting incredibly powerful! Hailuo AI just launched Seedance2.0 and ChatGPT Image 2. Now you can experience better models at a lower price, and enjoy unlimited free generation for GPT Image 2, Nano Banana 2 & Pro images. Many in film who skip AI will be left behind

AI is getting incredibly powerful! Hailuo AI just launched Seedance2.0 and ChatGPT Image 2. Now you can experience better models at a lower price, and enjoy unlimited free generation for GPT Image 2, Nano Banana 2 & Pro images. Many in film who skip AI will be left behind

Miguel Ángel | GptZone

100,266 次观看 • 4 个月前

Comparing Seedance 2.5 vs Seedance 2.0 👀 The native 30-second generation alone is a huge upgrade. But what about image quality, action scenes, fight choreography, prompt adherence, and overall consistency? Is the upgrade actually worth it? Full breakdown in the comments soon. 👇

Comparing Seedance 2.5 vs Seedance 2.0 👀 The native 30-second generation alone is a huge upgrade. But what about image quality, action scenes, fight choreography, prompt adherence, and overall consistency? Is the upgrade actually worth it? Full breakdown in the comments soon. 👇

JSFILMZ

11,672 次观看 • 24 天前