Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

𝗠𝗲𝘁𝗮𝗖𝗮𝗻𝘃𝗮𝘀 🎨 lets MLLMs "𝘥𝘳𝘢𝘧𝘵 𝘢𝘯𝘥 𝘥𝘳𝘢𝘸 𝘰𝘯 𝘢 𝘤𝘢𝘯𝘷𝘢𝘴" to guide diffusion generators. - canvas: spatial & temporal latents - gains on 6 tasks: T2I, T/I2V, image/video editing, in-context vgen. 📄 🌐

Ziqi Huang

2,682 subscribers

11,054 görüntüleme • 6 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Introducing Higgsfield Canvas: a state-of-the-art image editing model. Paint products directly onto your image with pixel-perfect control. Say hi to your new go-to for product placement, editing, and layout! 👋🏻 Comment Canvas to get the full guide in the DM.

Introducing Higgsfield Canvas: a state-of-the-art image editing model. Paint products directly onto your image with pixel-perfect control. Say hi to your new go-to for product placement, editing, and layout! 👋🏻 Comment Canvas to get the full guide in the DM.

Higgsfield AI 🧩

2,627,332 görüntüleme • 1 yıl önce

Introducing Modality Forcing, a recipe for post-training T2I models for SOTA RGB-Depth generation! Text-to-image (T2I) models learn rich representations of the spatial world. How do we build on this prior for high-quality depth generation? 🧵 [1/6]

Introducing Modality Forcing, a recipe for post-training T2I models for SOTA RGB-Depth generation! Text-to-image (T2I) models learn rich representations of the spatial world. How do we build on this prior for high-quality depth generation? 🧵 [1/6]

Bardienus Duisterhof

64,410 görüntüleme • 1 ay önce

video editing is stuck in 2005, time for something new introducing diffusion the first infinite canvas for video and motion graphics like figma, but for editing

video editing is stuck in 2005, time for something new introducing diffusion the first infinite canvas for video and motion graphics like figma, but for editing

konstantinpaulus

128,852 görüntüleme • 2 ay önce

Meta presents Video Editing via Factorized Diffusion Distillation We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video editing without relying on any supervised video editing data. To develop EVE we separately train an image editing

Meta presents Video Editing via Factorized Diffusion Distillation We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video editing without relying on any supervised video editing data. To develop EVE we separately train an image editing

AK

115,598 görüntüleme • 2 yıl önce

🕹️We are excited to introduce "ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation" ChronoEdit reframes image editing as a video generation task to encourage temporal consistency. It leverages a temporal reasoning stage that denoises with “video reasoning tokens” to "reason" on physically plausible edits. See the attached video for results. Project Page: Arxiv: Code and model are coming.

🕹️We are excited to introduce "ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation" ChronoEdit reframes image editing as a video generation task to encourage temporal consistency. It leverages a temporal reasoning stage that denoises with “video reasoning tokens” to "reason" on physically plausible edits. See the attached video for results. Project Page: Arxiv: Code and model are coming.

Huan Ling

36,869 görüntüleme • 9 ay önce

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

AK

40,474 görüntüleme • 2 yıl önce

(1/10) 🔥Thrilled to introduce OneDiffusion—our latest work in unified diffusion modeling! 🚀 This model bridges the gap between image synthesis and understanding, excelling in a wide range of tasks: T2I, conditional generation, image understanding, identity preservation, multiview generation, and even camera pose estimation. Learn more at: Project: arXiv: Code (on the way):

(1/10) 🔥Thrilled to introduce OneDiffusion—our latest work in unified diffusion modeling! 🚀 This model bridges the gap between image synthesis and understanding, excelling in a wide range of tasks: T2I, conditional generation, image understanding, identity preservation, multiview generation, and even camera pose estimation. Learn more at: Project: arXiv: Code (on the way):

Jiasen Lu

33,426 görüntüleme • 1 yıl önce

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

AK

718,760 görüntüleme • 3 yıl önce

🚨 Wan 2.7 is now live on fal! ⚡ Big upgrades in visuals, motion, audio, style, and consistency 🎬 First & last frame, 9-grid I2V, subject + voice reference 🎨 Instruction-based editing and video recreation

🚨 Wan 2.7 is now live on fal! ⚡ Big upgrades in visuals, motion, audio, style, and consistency 🎬 First & last frame, 9-grid I2V, subject + voice reference 🎨 Instruction-based editing and video recreation

fal

27,414 görüntüleme • 3 ay önce

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

AI at Meta

798,246 görüntüleme • 2 yıl önce

𝘐𝘵'𝘴 𝘢 𝘮𝘢𝘨𝘪𝘤𝘢𝘭 𝘵𝘩𝘪𝘯𝘨, 𝘵𝘩𝘦 𝘨𝘶𝘪𝘵𝘢𝘳. 𝘐𝘵 𝘢𝘭𝘭𝘰𝘸𝘴 𝘺𝘰𝘶 𝘵𝘰 𝘣𝘦 𝘵𝘩𝘦 𝘸𝘩𝘰𝘭𝘦 𝘣𝘢𝘯𝘥 𝘪𝘯 𝘰𝘯𝘦, 𝘵𝘰 𝘱𝘭𝘢𝘺 𝘳𝘩𝘺𝘵𝘩𝘮 𝘢𝘯𝘥 𝘮𝘦𝘭𝘰𝘥𝘺, 𝘴𝘪𝘯𝘨 𝘰𝘷𝘦𝘳 𝘵𝘩𝘦 𝘵𝘰𝘱. 𝘈𝘯𝘥 𝘢𝘴 𝘢𝘯 𝘪𝘯𝘴𝘵𝘳𝘶𝘮𝘦𝘯𝘵 𝘧𝘰𝘳 𝘴𝘰𝘭𝘰𝘴, 𝘺𝘰𝘶 𝘤𝘢𝘯 𝘣𝘦𝘯𝘥 𝘯𝘰𝘵𝘦𝘴, 𝘥𝘳𝘢𝘸 𝘦𝘮𝘰𝘵𝘪𝘰𝘯𝘢𝘭 𝘤𝘰𝘯𝘵𝘦𝘯𝘵 𝘰𝘶𝘵 𝘰𝘧 𝘵𝘪𝘯𝘺 𝘮𝘰𝘷𝘦𝘮𝘦𝘯𝘵𝘴, 𝘷𝘪𝘣𝘳𝘢𝘵𝘰𝘴 𝘢𝘯𝘥 𝘵𝘰𝘯𝘢𝘭 𝘵𝘩𝘪𝘯𝘨𝘴 𝘸𝘩𝘪𝘤𝘩 𝘦𝘷𝘦𝘯 𝘢 𝘱𝘪𝘢𝘯𝘰 𝘤𝘢𝘯'𝘵 𝘥𝘰. — 𝗗𝗮𝘃𝗶𝗱 𝗚𝗶𝗹𝗺𝗼𝘂𝗿

𝘐𝘵'𝘴 𝘢 𝘮𝘢𝘨𝘪𝘤𝘢𝘭 𝘵𝘩𝘪𝘯𝘨, 𝘵𝘩𝘦 𝘨𝘶𝘪𝘵𝘢𝘳. 𝘐𝘵 𝘢𝘭𝘭𝘰𝘸𝘴 𝘺𝘰𝘶 𝘵𝘰 𝘣𝘦 𝘵𝘩𝘦 𝘸𝘩𝘰𝘭𝘦 𝘣𝘢𝘯𝘥 𝘪𝘯 𝘰𝘯𝘦, 𝘵𝘰 𝘱𝘭𝘢𝘺 𝘳𝘩𝘺𝘵𝘩𝘮 𝘢𝘯𝘥 𝘮𝘦𝘭𝘰𝘥𝘺, 𝘴𝘪𝘯𝘨 𝘰𝘷𝘦𝘳 𝘵𝘩𝘦 𝘵𝘰𝘱. 𝘈𝘯𝘥 𝘢𝘴 𝘢𝘯 𝘪𝘯𝘴𝘵𝘳𝘶𝘮𝘦𝘯𝘵 𝘧𝘰𝘳 𝘴𝘰𝘭𝘰𝘴, 𝘺𝘰𝘶 𝘤𝘢𝘯 𝘣𝘦𝘯𝘥 𝘯𝘰𝘵𝘦𝘴, 𝘥𝘳𝘢𝘸 𝘦𝘮𝘰𝘵𝘪𝘰𝘯𝘢𝘭 𝘤𝘰𝘯𝘵𝘦𝘯𝘵 𝘰𝘶𝘵 𝘰𝘧 𝘵𝘪𝘯𝘺 𝘮𝘰𝘷𝘦𝘮𝘦𝘯𝘵𝘴, 𝘷𝘪𝘣𝘳𝘢𝘵𝘰𝘴 𝘢𝘯𝘥 𝘵𝘰𝘯𝘢𝘭 𝘵𝘩𝘪𝘯𝘨𝘴 𝘸𝘩𝘪𝘤𝘩 𝘦𝘷𝘦𝘯 𝘢 𝘱𝘪𝘢𝘯𝘰 𝘤𝘢𝘯'𝘵 𝘥𝘰. — 𝗗𝗮𝘃𝗶𝗱 𝗚𝗶𝗹𝗺𝗼𝘂𝗿

Prog Rock Songs

13,450 görüntüleme • 11 ay önce

PAIR-Diffusion: Object-Level Image Editing with Structure-and-Appearance Paired Diffusion Models Gradio demo is out on Hugging Face Spaces demo:

PAIR-Diffusion: Object-Level Image Editing with Structure-and-Appearance Paired Diffusion Models Gradio demo is out on Hugging Face Spaces demo:

AK

87,679 görüntüleme • 3 yıl önce

‘𝘚𝘩𝘦𝘳𝘪𝘥𝘢 𝘢𝘯𝘥 𝘋𝘢𝘯𝘪ë𝘭𝘭𝘦 𝘶𝘴𝘦𝘥 𝘵𝘰 𝘣𝘦 𝘰𝘯 𝘢 𝘱𝘰𝘴𝘵𝘦𝘳 𝘪𝘯 𝘮𝘺 𝘳𝘰𝘰𝘮’ 🧡🇳🇱 🆕 Day in the Life: Veerle Buurman! 🎥 🔗 #NothingLikeOranje #WEURO2025 | ING Nederland

‘𝘚𝘩𝘦𝘳𝘪𝘥𝘢 𝘢𝘯𝘥 𝘋𝘢𝘯𝘪ë𝘭𝘭𝘦 𝘶𝘴𝘦𝘥 𝘵𝘰 𝘣𝘦 𝘰𝘯 𝘢 𝘱𝘰𝘴𝘵𝘦𝘳 𝘪𝘯 𝘮𝘺 𝘳𝘰𝘰𝘮’ 🧡🇳🇱 🆕 Day in the Life: Veerle Buurman! 🎥 🔗 #NothingLikeOranje #WEURO2025 | ING Nederland

OranjeLeeuwinnen

13,469 görüntüleme • 1 yıl önce

This is a single uncut video, showing a robot learning several tasks instantly, after just one demonstration each ... This is possible because we've now been able to achieve in-context learning for everyday robotics tasks, and I'm very excited to announce our latest paper: 🎆 Instant Policy: In-Context Imitation Learning via Graph Diffusion 🎆 (1/6) 🧵👇

This is a single uncut video, showing a robot learning several tasks instantly, after just one demonstration each ... This is possible because we've now been able to achieve in-context learning for everyday robotics tasks, and I'm very excited to announce our latest paper: 🎆 Instant Policy: In-Context Imitation Learning via Graph Diffusion 🎆 (1/6) 🧵👇

Edward Johns

74,683 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

Can video generative models exhibit visuospatial intelligence? 🤔 Introducing Video4Spatial — a video-only framework that tackles spatial tasks. With just video context, our model can: 🔍 Ground objects by planning geometry-consistent paths 📸 Follow camera-pose instructions for scene navigation 🌐 Generalize to long contexts & unseen outdoor scenes A step toward video models as visual-spatial reasoners. Project: arXiv:

Can video generative models exhibit visuospatial intelligence? 🤔 Introducing Video4Spatial — a video-only framework that tackles spatial tasks. With just video context, our model can: 🔍 Ground objects by planning geometry-consistent paths 📸 Follow camera-pose instructions for scene navigation 🌐 Generalize to long contexts & unseen outdoor scenes A step toward video models as visual-spatial reasoners. Project: arXiv:

Xingang Pan

15,931 görüntüleme • 7 ay önce

FlowRVS - segmentation as a continuous deformation, mapping video latents directly to masks via an ODE. Built on Wan’s T2V. - complex semantic understanding with temporal consistency. - no flickering

FlowRVS - segmentation as a continuous deformation, mapping video latents directly to masks via an ODE. Built on Wan’s T2V. - complex semantic understanding with temporal consistency. - no flickering

Wildminder

26,559 görüntüleme • 4 ay önce

⌈ 𝑴𝒆𝒍𝒍𝒐 𝑪𝒉𝒊𝒃𝒊 𝑴𝒐𝒅𝒆𝒍 𝑮𝒊𝒗𝒆𝒂𝒘𝒂𝒚 ⌋ 『••✎••』 1 ᴡɪɴɴᴇʀ ᴡɪʟʟ ʀᴇᴄᴇɪᴠᴇ ᴀ ꜰᴜʟʟʏ ᴄᴏꜱᴛᴏᴍ ᴍᴇʟʟᴏ ᴍᴏᴅᴇʟ↷ ⨯ 𝘧𝘰𝘭𝘭𝘰𝘸 𝘮𝘦 𝘢𝘯𝘥 Nami Athena 🦈 | VGEN ⨯ 𝘳𝘦𝘱𝘰𝘴𝘵 ⨯ 𝘵𝘢𝘨 𝘢 𝘧𝘳𝘪𝘦𝘯𝘥 [#VtubersEN #VtuberSupport ]

⌈ 𝑴𝒆𝒍𝒍𝒐 𝑪𝒉𝒊𝒃𝒊 𝑴𝒐𝒅𝒆𝒍 𝑮𝒊𝒗𝒆𝒂𝒘𝒂𝒚 ⌋ 『••✎••』 1 ᴡɪɴɴᴇʀ ᴡɪʟʟ ʀᴇᴄᴇɪᴠᴇ ᴀ ꜰᴜʟʟʏ ᴄᴏꜱᴛᴏᴍ ᴍᴇʟʟᴏ ᴍᴏᴅᴇʟ↷ ⨯ 𝘧𝘰𝘭𝘭𝘰𝘸 𝘮𝘦 𝘢𝘯𝘥 Nami Athena 🦈 | VGEN ⨯ 𝘳𝘦𝘱𝘰𝘴𝘵 ⨯ 𝘵𝘢𝘨 𝘢 𝘧𝘳𝘪𝘦𝘯𝘥 [#VtubersEN #VtuberSupport ]

𓆩ɢᴏᴍɪ𓆪

130,067 görüntüleme • 2 yıl önce

1/ Excited to announce MoCA - a simple yet effective video editing method that accomplishes diverse spatial (style, background, object) and motion video edits using a motion conditioned image animation model.

1/ Excited to announce MoCA - a simple yet effective video editing method that accomplishes diverse spatial (style, background, object) and motion video edits using a motion conditioned image animation model.

Wilson Yan

10,636 görüntüleme • 2 yıl önce