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。

From LA to New York, the model continuously impresses me. This time utilizing an Image To World, the consistency in aesthetics from the input image is remarkable.

Theoretically Media

12,428 subscribers

34,467 次观看 • 7 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Gemini 3.1 Pro is the best model in the world for going from image to code. This task is basically solved now, kind of crazy. The model is now available in MagicPath.

Gemini 3.1 Pro is the best model in the world for going from image to code. This task is basically solved now, kind of crazy. The model is now available in MagicPath.

Pietro Schirano

219,529 次观看 • 7 个月前

My favorite demo of the new gpt-realtime model from Matthieu LC -- Shoggoth Mini using Realtime API with image input

My favorite demo of the new gpt-realtime model from Matthieu LC -- Shoggoth Mini using Realtime API with image input

Peter Bakkum

67,871 次观看 • 1 年前

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

Imagine a world where every image has a ZK verified checkmark, proving that the image came from an authentic camera, not generated by an AI model. threadguy wants to know, "Who's building this? I want to invest."

Imagine a world where every image has a ZK verified checkmark, proving that the image came from an authentic camera, not generated by an AI model. threadguy wants to know, "Who's building this? I want to invest."

Succinct

19,413 次观看 • 1 年前

Excited to share Muse Spark! It's a strong natively multimodal model with many surprising properties that emerged. Here, the model is able to use Python tools to make a playable Sudoku game on the web from an image input of the board. ✨

Excited to share Muse Spark! It's a strong natively multimodal model with many surprising properties that emerged. Here, the model is able to use Python tools to make a playable Sudoku game on the web from an image input of the board. ✨

Matt Deitke

29,702 次观看 • 5 个月前

Generative image to scene is getting incredibly good. This is pure 3D without v2v generated from the image in the reply ...

Generative image to scene is getting incredibly good. This is pure 3D without v2v generated from the image in the reply ...

martin_casado

57,176 次观看 • 1 年前

This scene was generated from one input image. Atlas fills the remaining gaps. → atlas (world labs) → spark.js → three.js

This scene was generated from one input image. Atlas fills the remaining gaps. → atlas (world labs) → spark.js → three.js

Ian Curtis

21,649 次观看 • 20 天前

Halfmoon is Reve Image — and it’s the best image model in the world 🥇 (🔊)

Halfmoon is Reve Image — and it’s the best image model in the world 🥇 (🔊)

Reve

547,266 次观看 • 1 年前

📢ProcGen3D: Learning Neural Procedural Graphs for Image-to-3D Reconstruction Xinyi Zhang learns neural procedural graphs to generate high-fidelity 3D - MCTS-guided sampling maintains consistency with the input image, even from real images! Check it out:

📢ProcGen3D: Learning Neural Procedural Graphs for Image-to-3D Reconstruction Xinyi Zhang learns neural procedural graphs to generate high-fidelity 3D - MCTS-guided sampling maintains consistency with the input image, even from real images! Check it out:

Angela Dai

14,680 次观看 • 10 个月前

We vibe coded this demo in Google AI Studio to show Nano Banana 2's real-world understanding. With each frame in this environment, the model sees only the previous image, and is prompted to imagine what happens next. The consistency is incredible!

We vibe coded this demo in Google AI Studio to show Nano Banana 2's real-world understanding. With each frame in this environment, the model sees only the previous image, and is prompted to imagine what happens next. The consistency is incredible!

Demis Hassabis

69,141 次观看 • 6 个月前

Today, we’re launching Reve 2.0, the best 4K image model in the world. We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

Today, we’re launching Reve 2.0, the best 4K image model in the world. We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

Reve

11,950,443 次观看 • 3 个月前

Seedream 5.0 Pro is now in ComfyUI via Partner Nodes. ByteDance's latest image model brings: → Character & product consistency across edits → Precision region editing → Infographics, flowcharts & structured layouts → In-image text across 14 languages One model. Text-to-image, editing, and multi-image inputs. Click the link below for the workflow 👇

Seedream 5.0 Pro is now in ComfyUI via Partner Nodes. ByteDance's latest image model brings: → Character & product consistency across edits → Precision region editing → Infographics, flowcharts & structured layouts → In-image text across 14 languages One model. Text-to-image, editing, and multi-image inputs. Click the link below for the workflow 👇

ComfyUI

14,756 次观看 • 2 个月前

F22 Fighter Pilot simulation with 1 input image with the incredible new #Genie3 from Google GoogleDeepMind

F22 Fighter Pilot simulation with 1 input image with the incredible new #Genie3 from Google GoogleDeepMind

GenMagnetic

60,948 次观看 • 7 个月前

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

Matthias Niessner

19,093 次观看 • 6 个月前

For this video created from an image in Grok Imagine, I combined two techniques: - the image editor from Grok Imagine - starting from a frame of a video to create other videos.

For this video created from an image in Grok Imagine, I combined two techniques: - the image editor from Grok Imagine - starting from a frame of a video to create other videos.

Déborah

21,960 次观看 • 8 个月前

"AI telephone" starts with an image -> GPT describes the image -> DALL-E makes an image from that description -> GPT describes the image -> DALL-E makes an image from that description, etc.... Experiment from my artist residency at OpenAI

"AI telephone" starts with an image -> GPT describes the image -> DALL-E makes an image from that description -> GPT describes the image -> DALL-E makes an image from that description, etc.... Experiment from my artist residency at OpenAI

Alexander Reben

39,236 次观看 • 2 年前

My first Google Veo 3.1 animated short 🤖 Made from one single image This is Bloom Using Scenebuilder and the New Insert function I was able to extend the scene and prompt new scenes from one hero image.

My first Google Veo 3.1 animated short 🤖 Made from one single image This is Bloom Using Scenebuilder and the New Insert function I was able to extend the scene and prompt new scenes from one hero image.

Dave Clark

167,731 次观看 • 11 个月前

Image analysis is now live for Pro users When you drag and drop an image into the input field Venice now auto-selects Qwen 2.5 VL 72B to analyze your image

Image analysis is now live for Pro users When you drag and drop an image into the input field Venice now auto-selects Qwen 2.5 VL 72B to analyze your image

Venice

53,786 次观看 • 1 年前