Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

InfinityStar by Bytedance: A unified 8B spacetime autoregressive model for high-res image & video gen; - 5s 720p video ~10x faster than DiT; - scores 83.74 on VBench, topping other AR models and HunyuanVideo; - Flan-T5-XL as text encoder. - 480/720p, ~35Gb model

wildmindai's profile picture

Wildminder

9,564 subscribers

23,255 Aufrufe • vor 11 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

🚀 SANA-Video 2.0 is here! A full-stack optimized video model designed for efficiency — while still delivering high quality. We combine a hybrid architecture closely related to the recent Kimi K3 design, adopt Self-Flow from FLUX 3, and further accelerate it with our own Sol-Engine. Key technical ingredients: 🧠 Hybrid Linear–Softmax Attention 3 gated linear layers + 1 gated-softmax anchor (75% linear / 25% softmax) 🧱 Block Attention Residuals (AttnRes) Boosts deep-layer effective rank by ~12% 🏗️ Unified 5B & 14B models Trained from scratch under very limited resources: • 5B → only 16 nodes of H100 • 14B → 48 nodes of B200 Results 📊 • 84.30 VBench Total • 3.2× faster DiT forward than matched full-softmax at 720p/60s • 720p/5s in 13.06s on a single H100 with Sol-Engine • 120× faster than Wan 2.2-A14B under the same one-H100 setup SANA-Video 2.0 shows that high-quality 720p video generation can be both efficient and practical on a single GPU. 🎬 Project: 📄 Paper: 💻 Code: Proud of the team! 🎉 More details below 🧵
0:24

🚀 SANA-Video 2.0 is here! A full-stack optimized video model designed for efficiency — while still delivering high quality. We combine a hybrid architecture closely related to the recent Kimi K3 design, adopt Self-Flow from FLUX 3, and further accelerate it with our own Sol-Engine. Key technical ingredients: 🧠 Hybrid Linear–Softmax Attention 3 gated linear layers + 1 gated-softmax anchor (75% linear / 25% softmax) 🧱 Block Attention Residuals (AttnRes) Boosts deep-layer effective rank by ~12% 🏗️ Unified 5B & 14B models Trained from scratch under very limited resources: • 5B → only 16 nodes of H100 • 14B → 48 nodes of B200 Results 📊 • 84.30 VBench Total • 3.2× faster DiT forward than matched full-softmax at 720p/60s • 720p/5s in 13.06s on a single H100 with Sol-Engine • 120× faster than Wan 2.2-A14B under the same one-H100 setup SANA-Video 2.0 shows that high-quality 720p video generation can be both efficient and practical on a single GPU. 🎬 Project: 📄 Paper: 💻 Code: Proud of the team! 🎉 More details below 🧵

Enze Xie

25,595 Aufrufe • vor 2 Monaten

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:
1:39

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 Aufrufe • vor 1 Jahr

P-Video-Animate is now the fastest model for top-quality image-to-video motion transfer. - $0.03/s at 720p and $0.06/s at 1080p — a fraction of typical motion-transfer pricing (~$0.07–$0.35/s at 720p in our benchmarks) - 5.24 s generation time per second of output video at 720p — roughly 7× faster than typical motion-transfer alternatives in the same benchmarks - Upload one still plus a driver video to preserve motion, timing, camera movement, and scene structure, with optional source audio and clips up to ~2 minutes at 720p Ideal for UGC ads, gaming cinematics, film casting, and product demos when you already have a winning take and want a new hero still to follow it. Try it in the playground: We’re launching with 70% discounted usage for the coming two days with our launch partners. each::labs, Replicate, Runware, Scenario, WaveSpeedAI, Wiro, Tellers, Soon also on Together AI We’d love your feedback as you try it. 📚 Model docs & API examples: 📚 API quickstart: ⭐️ OSS: 🌐
1:03

P-Video-Animate is now the fastest model for top-quality image-to-video motion transfer. - $0.03/s at 720p and $0.06/s at 1080p — a fraction of typical motion-transfer pricing (~$0.07–$0.35/s at 720p in our benchmarks) - 5.24 s generation time per second of output video at 720p — roughly 7× faster than typical motion-transfer alternatives in the same benchmarks - Upload one still plus a driver video to preserve motion, timing, camera movement, and scene structure, with optional source audio and clips up to ~2 minutes at 720p Ideal for UGC ads, gaming cinematics, film casting, and product demos when you already have a winning take and want a new hero still to follow it. Try it in the playground: We’re launching with 70% discounted usage for the coming two days with our launch partners. each::labs, Replicate, Runware, Scenario, WaveSpeedAI, Wiro, Tellers, Soon also on Together AI We’d love your feedback as you try it. 📚 Model docs & API examples: 📚 API quickstart: ⭐️ OSS: 🌐

Pruna AI

22,727 Aufrufe • vor 4 Monaten

𝗔𝗴𝗻𝗲𝘀 𝟮.𝟬 𝗶𝘀 𝗳𝗿𝗲𝗲. 𝗜𝗻𝗱𝗲𝗳𝗶𝗻𝗶𝘁𝗲𝗹𝘆. 𝗡𝗼 𝘄𝗮𝗶𝘁𝗹𝗶𝘀𝘁. Text. Image. Video. One model series. We built Agnes-2.0 for the developers who got priced out — high token costs, API limits, geography. That ends today. 𝗪𝗵𝗮𝘁'𝘀 𝗹𝗶𝘃𝗲: → 𝗔𝗴𝗻𝗲𝘀-𝟮.𝟬-𝗙𝗹𝗮𝘀𝗵 — text and agentic, top 10 on Claw-Eval, ahead of Gemini and MiniMax → 𝗔𝗴𝗻𝗲𝘀-𝗜𝗺𝗮𝗴𝗲-𝟮.𝟬-𝗙𝗹𝗮𝘀𝗵 — image editing, top 10 on Artificial Analysis → 𝗔𝗴𝗻𝗲𝘀-𝗩𝗶𝗱𝗲𝗼-𝗩𝟮.𝟬 — text-to-video, image-to-video, native audio, top 10 on Artificial Analysis These are not demo models. Not stripped-down trials. The same production models that benchmark globally alongside OpenAI, Google, Anthropic, KlingAI, and ByteDance. Trained in Singapore. Ranked globally. Free today. 𝗻𝗼 𝘀𝘂𝗯𝘀𝗰𝗿𝗶𝗽𝘁𝗶𝗼𝗻 𝗻𝗲𝗲𝗱𝗲𝗱.
2:20

𝗔𝗴𝗻𝗲𝘀 𝟮.𝟬 𝗶𝘀 𝗳𝗿𝗲𝗲. 𝗜𝗻𝗱𝗲𝗳𝗶𝗻𝗶𝘁𝗲𝗹𝘆. 𝗡𝗼 𝘄𝗮𝗶𝘁𝗹𝗶𝘀𝘁. Text. Image. Video. One model series. We built Agnes-2.0 for the developers who got priced out — high token costs, API limits, geography. That ends today. 𝗪𝗵𝗮𝘁'𝘀 𝗹𝗶𝘃𝗲: → 𝗔𝗴𝗻𝗲𝘀-𝟮.𝟬-𝗙𝗹𝗮𝘀𝗵 — text and agentic, top 10 on Claw-Eval, ahead of Gemini and MiniMax → 𝗔𝗴𝗻𝗲𝘀-𝗜𝗺𝗮𝗴𝗲-𝟮.𝟬-𝗙𝗹𝗮𝘀𝗵 — image editing, top 10 on Artificial Analysis → 𝗔𝗴𝗻𝗲𝘀-𝗩𝗶𝗱𝗲𝗼-𝗩𝟮.𝟬 — text-to-video, image-to-video, native audio, top 10 on Artificial Analysis These are not demo models. Not stripped-down trials. The same production models that benchmark globally alongside OpenAI, Google, Anthropic, KlingAI, and ByteDance. Trained in Singapore. Ranked globally. Free today. 𝗻𝗼 𝘀𝘂𝗯𝘀𝗰𝗿𝗶𝗽𝘁𝗶𝗼𝗻 𝗻𝗲𝗲𝗱𝗲𝗱.

Agnes AI

3,526,373 Aufrufe • vor 4 Monaten

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.
0:30

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.

AI at Meta

2,267,059 Aufrufe • vor 2 Jahren

Exciting milestones in our generative AI research: Emu Video, which lets you create high quality videos from a text prompt, and Emu Edit, which enables detailed image editing based on your instructions. These new models are built on Emu, our foundation model for image generation and technology from them will underpin new creative features across our apps next year. Try it out: Emu Video: Emu Edit:
0:37

Exciting milestones in our generative AI research: Emu Video, which lets you create high quality videos from a text prompt, and Emu Edit, which enables detailed image editing based on your instructions. These new models are built on Emu, our foundation model for image generation and technology from them will underpin new creative features across our apps next year. Try it out: Emu Video: Emu Edit:

Boz

110,735 Aufrufe • vor 2 Jahren

zeroscope_v2 XL, A watermark-free Modelscope-based video model capable of generating high quality video at 1024 x 576 Model on Hugging Face : This model was trained with offset noise using 9,923 clips and 29,769 tagged frames at 24 frames, 1024x576 resolution. zeroscope_v2_XL is specifically designed for upscaling content made with zeroscope_v2_576w using vid2vid in the 1111 text2video extension by kabachuha. Leveraging this model as an upscaler allows for superior overall compositions at higher resolutions, permitting faster exploration in 576x320 (or 448x256) before transitioning to a high-resolution render. zeroscope_v2_XL uses 15.3gb of vram when rendering 30 frames at 1024x576
0:35

zeroscope_v2 XL, A watermark-free Modelscope-based video model capable of generating high quality video at 1024 x 576 Model on Hugging Face : This model was trained with offset noise using 9,923 clips and 29,769 tagged frames at 24 frames, 1024x576 resolution. zeroscope_v2_XL is specifically designed for upscaling content made with zeroscope_v2_576w using vid2vid in the 1111 text2video extension by kabachuha. Leveraging this model as an upscaler allows for superior overall compositions at higher resolutions, permitting faster exploration in 576x320 (or 448x256) before transitioning to a high-resolution render. zeroscope_v2_XL uses 15.3gb of vram when rendering 30 frames at 1024x576

AK

714,563 Aufrufe • vor 3 Jahren

We are excited to unveil HunyuanVideo 1.5, the strongest open-source video generation model. Built upon DiT architecture, it redefines the open-source SOTA for accessibility and performance.🚀🚀🚀 HunyuanVideo 1.5 delivers state-of-the-art visual quality and motion coherence while drastically lowering the entry barrier for developers and creators: ⚡️ Unmatched Accessibility: Ultra-light 8.3B parameters, deployable on consumer GPUs with only 14GB VRAM. 🖥️ HD Cinematic Quality: Natively generates 5–10 second 480p/720p HD videos, with super-resolution support for 1080p cinematic quality. By merging SOTA performance with high hardware efficiency, HunyuanVideo 1.5 sets the new technical baseline for the open-source community. 🌐Project Page: 🔗Github: 🤗Hugging Face： 📄Technical Report:
1:03

We are excited to unveil HunyuanVideo 1.5, the strongest open-source video generation model. Built upon DiT architecture, it redefines the open-source SOTA for accessibility and performance.🚀🚀🚀 HunyuanVideo 1.5 delivers state-of-the-art visual quality and motion coherence while drastically lowering the entry barrier for developers and creators: ⚡️ Unmatched Accessibility: Ultra-light 8.3B parameters, deployable on consumer GPUs with only 14GB VRAM. 🖥️ HD Cinematic Quality: Natively generates 5–10 second 480p/720p HD videos, with super-resolution support for 1080p cinematic quality. By merging SOTA performance with high hardware efficiency, HunyuanVideo 1.5 sets the new technical baseline for the open-source community. 🌐Project Page: 🔗Github: 🤗Hugging Face： 📄Technical Report:

Tencent Hy

128,008 Aufrufe • vor 10 Monaten

Meta announces Movie Gen A Cast of Media Foundation Models We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user’s image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models
0:30

Meta announces Movie Gen A Cast of Media Foundation Models We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user’s image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models

AK

62,719 Aufrufe • vor 2 Jahren

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.
0:36

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 Aufrufe • vor 3 Jahren

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️
2:10

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

AI at Meta

163,575 Aufrufe • vor 1 Jahr

Images, video, audio, actions — generative modeling has converged on one recipe: compress into continuous latents, generate in latent space, decode. Language is the lone exception: still generated token by token, as a long discrete stream. Latent Thought Flows: We compress 256 text tokens into 8 continuous latents, generate them with a one-step flow model, and read them out as text using an autoregressive decoder. Result: a better inference-compute vs. generation-quality Pareto frontier than a tuned autoregressive baseline — thanks to compression and one-step generation. Co-led w/ Zhengyang Geng 🧵
1:02

Images, video, audio, actions — generative modeling has converged on one recipe: compress into continuous latents, generate in latent space, decode. Language is the lone exception: still generated token by token, as a long discrete stream. Latent Thought Flows: We compress 256 text tokens into 8 continuous latents, generate them with a one-step flow model, and read them out as text using an autoregressive decoder. Result: a better inference-compute vs. generation-quality Pareto frontier than a tuned autoregressive baseline — thanks to compression and one-step generation. Co-led w/ Zhengyang Geng 🧵

Mihir Prabhudesai

82,784 Aufrufe • vor 2 Monaten

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.
1:43

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

40,490 Aufrufe • vor 2 Jahren

P-Video-Replace is now the fastest model for top-quality character replacement in existing video. - $0.03/s at 720p and $0.06/s at 1080p — a small fraction of typical character-replacement / video-edit pricing (~$0.07–$0.35/s at 720p in our benchmarks) - 3.58 s generation time per second of output video at 720p — roughly ~10× faster than typical alternatives in the same benchmarks (~36–43 s per second of output) - Upload a source video, 1–4 reference character images, and an instruction prompt to swap the character in the source video while keeping the rest unchanged. Ideal for UGC ad variations, meme remixes, film recasting, gaming cinematics, and educational videos when you already have a winning take and need a new face, creator, or persona in the same shot. Try it in the playground: We're launching with 70% discounted usage which ends on 2026-06-08 00:00 CEST! Try it at any of our launch partners: Pruna AI, each::labs, inference shell, Replicate, Runware, Scenario, Tellers, Together AI, WaveSpeedAI, Wiro AI — Ship AI Faster Also available on the Pruna API: We'd love your feedback as you try it. 📚 Model docs & API examples: 📚 API quickstart: ⭐️ OSS: 🌐
1:09

P-Video-Replace is now the fastest model for top-quality character replacement in existing video. - $0.03/s at 720p and $0.06/s at 1080p — a small fraction of typical character-replacement / video-edit pricing (~$0.07–$0.35/s at 720p in our benchmarks) - 3.58 s generation time per second of output video at 720p — roughly ~10× faster than typical alternatives in the same benchmarks (~36–43 s per second of output) - Upload a source video, 1–4 reference character images, and an instruction prompt to swap the character in the source video while keeping the rest unchanged. Ideal for UGC ad variations, meme remixes, film recasting, gaming cinematics, and educational videos when you already have a winning take and need a new face, creator, or persona in the same shot. Try it in the playground: We're launching with 70% discounted usage which ends on 2026-06-08 00:00 CEST! Try it at any of our launch partners: Pruna AI, each::labs, inference shell, Replicate, Runware, Scenario, Tellers, Together AI, WaveSpeedAI, Wiro AI — Ship AI Faster Also available on the Pruna API: We'd love your feedback as you try it. 📚 Model docs & API examples: 📚 API quickstart: ⭐️ OSS: 🌐

Pruna AI

20,098 Aufrufe • vor 4 Monaten

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:
2:09

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

413,175 Aufrufe • vor 1 Jahr

StyleDrop: Text-to-Image Generation in Any Style introduce StyleDrop, a method that enables the synthesis of images that faithfully follow a specific style using a text-to-image model. The proposed method is extremely versatile and captures nuances and details of a user-provided style, such as color schemes, shading, design patterns, and local and global effects. It efficiently learns a new style by fine-tuning very few trainable parameters (less than 1% of total model parameters) and improving the quality via iterative training with either human or automated feedback. Better yet, StyleDrop is able to deliver impressive results even when the user supplies only a single image that specifies the desired style. An extensive study shows that, for the task of style tuning text-to-image models, StyleDrop implemented on Muse convincingly outperforms other methods, including DreamBooth and textual inversion on Imagen or Stable Diffusion. paper page:
1:56

StyleDrop: Text-to-Image Generation in Any Style introduce StyleDrop, a method that enables the synthesis of images that faithfully follow a specific style using a text-to-image model. The proposed method is extremely versatile and captures nuances and details of a user-provided style, such as color schemes, shading, design patterns, and local and global effects. It efficiently learns a new style by fine-tuning very few trainable parameters (less than 1% of total model parameters) and improving the quality via iterative training with either human or automated feedback. Better yet, StyleDrop is able to deliver impressive results even when the user supplies only a single image that specifies the desired style. An extensive study shows that, for the task of style tuning text-to-image models, StyleDrop implemented on Muse convincingly outperforms other methods, including DreamBooth and textual inversion on Imagen or Stable Diffusion. paper page:

AK

56,402 Aufrufe • vor 3 Jahren

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale blog: Large-scale generative models such as GPT and DALL-E have revolutionized natural language processing and computer vision research. These models not only generate high fidelity text or image outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are neither filtered nor enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster.
2:43

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale blog: Large-scale generative models such as GPT and DALL-E have revolutionized natural language processing and computer vision research. These models not only generate high fidelity text or image outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are neither filtered nor enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster.

AK

429,355 Aufrufe • vor 3 Jahren

Meta just announced FlowVid Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis paper page: Diffusion models have transformed the image-to-image (I2I) synthesis and are now permeating into videos. However, the advancement of video-to-video (V2V) synthesis has been hampered by the challenge of maintaining temporal consistency across video frames. This paper proposes a consistent V2V synthesis framework by jointly leveraging spatial conditions and temporal optical flow clues within the source video. Contrary to prior methods that strictly adhere to optical flow, our approach harnesses its benefits while handling the imperfection in flow estimation. We encode the optical flow via warping from the first frame and serve it as a supplementary reference in the diffusion model. This enables our model for video synthesis by editing the first frame with any prevalent I2I models and then propagating edits to successive frames. Our V2V model, FlowVid, demonstrates remarkable properties: (1) Flexibility: FlowVid works seamlessly with existing I2I models, facilitating various modifications, including stylization, object swaps, and local edits. (2) Efficiency: Generation of a 4-second video with 30 FPS and 512x512 resolution takes only 1.5 minutes, which is 3.1x, 7.2x, and 10.5x faster than CoDeF, Rerender, and TokenFlow, respectively. (3) High-quality: In user studies, our FlowVid is preferred 45.7% of the time, outperforming CoDeF (3.5%), Rerender (10.2%), and TokenFlow (40.4%).
0:47

Meta just announced FlowVid Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis paper page: Diffusion models have transformed the image-to-image (I2I) synthesis and are now permeating into videos. However, the advancement of video-to-video (V2V) synthesis has been hampered by the challenge of maintaining temporal consistency across video frames. This paper proposes a consistent V2V synthesis framework by jointly leveraging spatial conditions and temporal optical flow clues within the source video. Contrary to prior methods that strictly adhere to optical flow, our approach harnesses its benefits while handling the imperfection in flow estimation. We encode the optical flow via warping from the first frame and serve it as a supplementary reference in the diffusion model. This enables our model for video synthesis by editing the first frame with any prevalent I2I models and then propagating edits to successive frames. Our V2V model, FlowVid, demonstrates remarkable properties: (1) Flexibility: FlowVid works seamlessly with existing I2I models, facilitating various modifications, including stylization, object swaps, and local edits. (2) Efficiency: Generation of a 4-second video with 30 FPS and 512x512 resolution takes only 1.5 minutes, which is 3.1x, 7.2x, and 10.5x faster than CoDeF, Rerender, and TokenFlow, respectively. (3) High-quality: In user studies, our FlowVid is preferred 45.7% of the time, outperforming CoDeF (3.5%), Rerender (10.2%), and TokenFlow (40.4%).

AK

123,729 Aufrufe • vor 2 Jahren

Explore state-of-the-art multimodal prompting in our new short course Large Multimodal Model Prompting with Gemini, taught by Erwin Huizenga in collaboration with Google Cloud. One interesting insight from this course: with multimodal models, prompt structure matters significantly. Placing text inputs, such as a patient's medical history, before image inputs, like an X-ray, can enhance the model's ability to contextualize and interpret visual data effectively. In other contexts, such as image captioning, you may get better results by putting the image first. Multimodal models behave differently than text-only LLMs, and effective prompting for models varies depending on the model you’re using. In this course you’ll learn how to effectively prompt Gemini models. Gemini's multimodal capabilities also enable new approaches in AI application development, for example: - The Gemini library handles various video formats (MP4, MOV, MPEG), streamlining applications using these formats. - Large context window (up to 1 million tokens) enables processing of extensive content, like analyzing multiple 50-minute videos simultaneously. - Function calling feature integrates real-time data (e.g., current exchange rates) into model responses. The course demonstrates building multimodal applications with real-world examples including document analyzers that reason across text and graphs simultaneously, video content extractors that find and timestamp specific information from multiple hours of footage, and automated expense report systems processing receipt images while cross-referencing company policies. Sign up here:
2:49

Explore state-of-the-art multimodal prompting in our new short course Large Multimodal Model Prompting with Gemini, taught by Erwin Huizenga in collaboration with Google Cloud. One interesting insight from this course: with multimodal models, prompt structure matters significantly. Placing text inputs, such as a patient's medical history, before image inputs, like an X-ray, can enhance the model's ability to contextualize and interpret visual data effectively. In other contexts, such as image captioning, you may get better results by putting the image first. Multimodal models behave differently than text-only LLMs, and effective prompting for models varies depending on the model you’re using. In this course you’ll learn how to effectively prompt Gemini models. Gemini's multimodal capabilities also enable new approaches in AI application development, for example: - The Gemini library handles various video formats (MP4, MOV, MPEG), streamlining applications using these formats. - Large context window (up to 1 million tokens) enables processing of extensive content, like analyzing multiple 50-minute videos simultaneously. - Function calling feature integrates real-time data (e.g., current exchange rates) into model responses. The course demonstrates building multimodal applications with real-world examples including document analyzers that reason across text and graphs simultaneously, video content extractors that find and timestamp specific information from multiple hours of footage, and automated expense report systems processing receipt images while cross-referencing company policies. Sign up here:

Andrew Ng

74,060 Aufrufe • vor 2 Jahren