Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

some cool stuff from Google! Dropped an Interactive Video Super-Resolution - SparkVSR - CogVideoX1.5-5B; - propagates high-quality textures from edited keyframes across sequences; - tops DOVE and STAR, +24.6% on CLIP-IQA and +21.8% on DOVER; - zero-shot restoration, colorization, style transfer! - beats FlashVSR

Wildminder

10,441 subscribers

19,852 просмотров • 4 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Wow! Super impressive work by the new Amazon FAR team (from Covariant acquisition). Mapping long sequences of human motion (>30 sec) on robots with a differing shapes or interating with objects (box, table, etc) of different size. Enabling easier in-simulation data-augmentation and zero-shoot transfer. Super impressive and huge help to reduce the need for human teleop data (which is very complex to gather for humanoids) Dataset trajectories on Hugging Face (search OmniRetarget), full code framework to come soon Project page has some pretty three.js interactive demos

Wow! Super impressive work by the new Amazon FAR team (from Covariant acquisition). Mapping long sequences of human motion (>30 sec) on robots with a differing shapes or interating with objects (box, table, etc) of different size. Enabling easier in-simulation data-augmentation and zero-shoot transfer. Super impressive and huge help to reduce the need for human teleop data (which is very complex to gather for humanoids) Dataset trajectories on Hugging Face (search OmniRetarget), full code framework to come soon Project page has some pretty three.js interactive demos

Thomas Wolf

149,734 просмотров • 9 месяцев назад

Why do most humanoid motion trackers still slip, skate, or clip through objects? Because the real bottleneck isn’t RL, it’s bad retargeting… OmniRetarget flips the script: instead of compensating with dozens of reward terms, it generates high-quality, interaction-preserving trajectories from human motions. The result is agile, human-like skills with minimal RL. ✅ 5 reward terms, 4 domain randomization terms, proprioception only, no history or curriculum ✅ Interaction mesh produces clean, contact-preserving motions with virtually no foot-skating ✅ Works across embodiments (Unitree H1, Booster T1) and scales from one demo to many scenes From carrying boxes to slope crawling to parkour-style rolls, policies trained on OmniRetarget data transfer zero-shot from sim to real hardware. Thanks for sharing, Zhen Wu! 📍Paper: Website: Dataset:

Why do most humanoid motion trackers still slip, skate, or clip through objects? Because the real bottleneck isn’t RL, it’s bad retargeting… OmniRetarget flips the script: instead of compensating with dozens of reward terms, it generates high-quality, interaction-preserving trajectories from human motions. The result is agile, human-like skills with minimal RL. ✅ 5 reward terms, 4 domain randomization terms, proprioception only, no history or curriculum ✅ Interaction mesh produces clean, contact-preserving motions with virtually no foot-skating ✅ Works across embodiments (Unitree H1, Booster T1) and scales from one demo to many scenes From carrying boxes to slope crawling to parkour-style rolls, policies trained on OmniRetarget data transfer zero-shot from sim to real hardware. Thanks for sharing, Zhen Wu! 📍Paper: Website: Dataset:

Ilir Aliu - eu/acc

61,491 просмотров • 9 месяцев назад

1/ 🧠Humans are the best robot data source! 2/ 👓Human egocentric video is rich in quantity, but poor in quality. 3/ Beyond scaling data, smarter representation and architecture matter just as much. 4/ Want an open-source framework to train your own learn-from-human-data robot policy? 🚀We introduce HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Robot-Data-Free ✦ Just 30 min of data per task ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Easy-to-Implement Let's squeeze every bit of signal out of human data! 🌐 Website: 📄 Paper: 💻 Code: 📹 Video: 🧵 1/n

1/ 🧠Humans are the best robot data source! 2/ 👓Human egocentric video is rich in quantity, but poor in quality. 3/ Beyond scaling data, smarter representation and architecture matter just as much. 4/ Want an open-source framework to train your own learn-from-human-data robot policy? 🚀We introduce HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Robot-Data-Free ✦ Just 30 min of data per task ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Easy-to-Implement Let's squeeze every bit of signal out of human data! 🌐 Website: 📄 Paper: 💻 Code: 📹 Video: 🧵 1/n

Zhi (Leo) Wang

109,595 просмотров • 1 месяц назад

I spent 3 minutes editing a video I would've reshoot for an entire day. Runway just dropped Aleph 2.0, and it's not another "generate from scratch" AI tool. It edits footage you already have. Here's what that actually means: - You type the change. One sentence. - It applies across the entire clip. Multi-shot sequences included. - Only what you asked changes. Background, lighting, and motion all untouched. - Preview before you commit. No blind generations. I tested it with a product color swap: same clip, different color, same everything else. The output looked like a separate shoot. For anyone running ads or producing content variants, this is the tool. One clip, multiple deliverables, zero reshoots. Live now → Code ALEPH2 = 22% off 2 months of Pro (till May 31) ⚡ #MadeWithRunway Runway #ad

I spent 3 minutes editing a video I would've reshoot for an entire day. Runway just dropped Aleph 2.0, and it's not another "generate from scratch" AI tool. It edits footage you already have. Here's what that actually means: - You type the change. One sentence. - It applies across the entire clip. Multi-shot sequences included. - Only what you asked changes. Background, lighting, and motion all untouched. - Preview before you commit. No blind generations. I tested it with a product color swap: same clip, different color, same everything else. The output looked like a separate shoot. For anyone running ads or producing content variants, this is the tool. One clip, multiple deliverables, zero reshoots. Live now → Code ALEPH2 = 22% off 2 months of Pro (till May 31) ⚡ #MadeWithRunway Runway #ad

CODIFY

40,843 просмотров • 1 месяц назад

Google DeepMind just dropped 'Genie', an AI that can generate interactive video games. This is a huge deal. Genie is trained on 200,000 hours of unsupervised public internet gaming videos and can generate video games from a single prompt or image. But here's what's insane: Despite not being trained on action or text annotations, the foundation model can determine who the main character is and enable a user to control that character in the generated world. It does this through its Latent Action Model, Video Tokenizer, and Dynamics Model (will go more in-depth on this in tomorrow's newsletter for those interested). And for those asking, yes, it's research-only and not publicly available (here come the Google memes), and it does come with some limitations, like only currently creating games at 1FPS. But this is the worst AI will ever be. Anyone will be able to create their own entirely imagined virtual worlds soon, and that's a wild sentence to say out loud.

Google DeepMind just dropped 'Genie', an AI that can generate interactive video games. This is a huge deal. Genie is trained on 200,000 hours of unsupervised public internet gaming videos and can generate video games from a single prompt or image. But here's what's insane: Despite not being trained on action or text annotations, the foundation model can determine who the main character is and enable a user to control that character in the generated world. It does this through its Latent Action Model, Video Tokenizer, and Dynamics Model (will go more in-depth on this in tomorrow's newsletter for those interested). And for those asking, yes, it's research-only and not publicly available (here come the Google memes), and it does come with some limitations, like only currently creating games at 1FPS. But this is the worst AI will ever be. Anyone will be able to create their own entirely imagined virtual worlds soon, and that's a wild sentence to say out loud.

Rowan Cheung

3,376,915 просмотров • 2 лет назад

Co-produced with PAI by Utopai Studios, the first long-form video generation model. The AI video clip era is ending! I started with a short story idea. From there, PAI generated the characters, transformed them into keyframes, and then animated the scenes into a full sequence. The interesting part was seeing how the same characters, environment, and visual style stayed consistent across multiple shots while the story progressed naturally. What felt different here is that I wasn’t building each shot manually. I focused on the narrative, and the engine handled character creation, scene continuity, and animation to produce a ready-to-watch video. A step-by-step tutorial so you can make your own story 👇🏻 Thanks to Utopai Studios for collaborating with me Try it now: #UtopaiPartners

Co-produced with PAI by Utopai Studios, the first long-form video generation model. The AI video clip era is ending! I started with a short story idea. From there, PAI generated the characters, transformed them into keyframes, and then animated the scenes into a full sequence. The interesting part was seeing how the same characters, environment, and visual style stayed consistent across multiple shots while the story progressed naturally. What felt different here is that I wasn’t building each shot manually. I focused on the narrative, and the engine handled character creation, scene continuity, and animation to produce a ready-to-watch video. A step-by-step tutorial so you can make your own story 👇🏻 Thanks to Utopai Studios for collaborating with me Try it now: #UtopaiPartners

Amira Zairi

25,679 просмотров • 4 месяцев назад

GPT image 2 for storyboard and Seedence 2.0 for video on OpenArt In a village consumed by fear hope arrived with a sword. Prompt: Create a cinematic anime short film in a unified Demon Slayer / Jujutsu Kaisen inspired art style — apply this exact same visual style consistently to ALL characters and scenes without exception. Character Design (maintain throughout ALL scenes): Hero: Young male swordsman, late teens, athletic build, dark hair, determined eyes, traditional Japanese warrior outfit, katana at waist Child: Small baby girl, 2–3 years old, round face, big innocent eyes, simple village dress, same anime art style as the hero — no style deviation Story Structure: Opening — Close-up on hero's face receiving urgent message. Camera: low angle looking up at hero. Dramatic lighting. Journey — Hero running through dense forest and rocky mountains. Camera: dynamic tracking shot from side, then bird's eye view. Motion blur on feet. Village in Crisis — Wide establishing shot of burning village. Cut to medium shot of terrified villagers. Camera slowly pushes in. Monster threatening child — Monster looms over baby girl. Camera: monster POV looking down at child, then child POV looking up at monster. High contrast lighting. Hero Arrival — Hero leaps into frame from above. Slow motion sword strike. Camera: 360-degree rotating shot around hero. Battle Sequence — Intense fight, multiple camera angles: close-up on clashing sword, wide shot of full battle, low angle hero power move. Fluid motion, no flickering. Resolution — Monster defeated. Hero kneels down to baby girl's level. Soft warm lighting. Camera: gentle zoom out showing hero and child together, villagers in background. Ending — Hero sheathes sword, walks away. Camera: back shot of hero walking into sunset, villagers watching. Visual Rules (strict): One unified anime art style across ALL shots — hero and baby girl must look like they belong in the same animation Camera angle must change every scene — no repeated angles No slideshow transitions — use cinematic cuts and motion Warm golden lighting for resolution, cool blue for battle Pippit watermark visible in final composition Style: Epic fantasy anime, Demon Slayer quality, emotional storytelling, professional cinematic pacing

GPT image 2 for storyboard and Seedence 2.0 for video on OpenArt In a village consumed by fear hope arrived with a sword. Prompt: Create a cinematic anime short film in a unified Demon Slayer / Jujutsu Kaisen inspired art style — apply this exact same visual style consistently to ALL characters and scenes without exception. Character Design (maintain throughout ALL scenes): Hero: Young male swordsman, late teens, athletic build, dark hair, determined eyes, traditional Japanese warrior outfit, katana at waist Child: Small baby girl, 2–3 years old, round face, big innocent eyes, simple village dress, same anime art style as the hero — no style deviation Story Structure: Opening — Close-up on hero's face receiving urgent message. Camera: low angle looking up at hero. Dramatic lighting. Journey — Hero running through dense forest and rocky mountains. Camera: dynamic tracking shot from side, then bird's eye view. Motion blur on feet. Village in Crisis — Wide establishing shot of burning village. Cut to medium shot of terrified villagers. Camera slowly pushes in. Monster threatening child — Monster looms over baby girl. Camera: monster POV looking down at child, then child POV looking up at monster. High contrast lighting. Hero Arrival — Hero leaps into frame from above. Slow motion sword strike. Camera: 360-degree rotating shot around hero. Battle Sequence — Intense fight, multiple camera angles: close-up on clashing sword, wide shot of full battle, low angle hero power move. Fluid motion, no flickering. Resolution — Monster defeated. Hero kneels down to baby girl's level. Soft warm lighting. Camera: gentle zoom out showing hero and child together, villagers in background. Ending — Hero sheathes sword, walks away. Camera: back shot of hero walking into sunset, villagers watching. Visual Rules (strict): One unified anime art style across ALL shots — hero and baby girl must look like they belong in the same animation Camera angle must change every scene — no repeated angles No slideshow transitions — use cinematic cuts and motion Warm golden lighting for resolution, cool blue for battle Pippit watermark visible in final composition Style: Epic fantasy anime, Demon Slayer quality, emotional storytelling, professional cinematic pacing

𝗦𝗮𝗻𝗶𝗮

13,712 просмотров • 1 месяц назад

Apple Maps 3d is insanely impressive now (see video below) Google on the other hand decided to build an insanely clunky solution to display 3d maps to avoid using mobile GPUs: A Google server streams (!) a live video of its 3d rendered map to you, the result is a disastrous: a super laggy and clunky 3d view full of video compression artefacts with a response time of 2-3 seconds for every movement And I know WHY they built that, someone felt it was not inclusive to only have 3d maps that are high performing on iOS because Apple's GPUs are insanely fast and can deal with it (as you can see below in Apple Maps) but they wanted to support inferior phones, I get it But then they also decided to worsen the experience for iOS users who could easily run 3d natively on its GPU It's just an insane product decision, there's no way to cut it: they could have super smooth 3d like Apple Maps but neutered it with a clunky live stream Even more insane because Google does have native 3d on iOS in a completely different app that nobody uses: Google Earth Is 3d important? Not rly for nav no but it shows again something about Google's engineering decisions, like the redesign of the Google OAuth Login screen that made zero sense Nobody is speaking up against bad ideas in Google meetings, everyone's too scared of HR maybe, it's the opposite of a meritocracy and it's just super visible from using Google products right now

Apple Maps 3d is insanely impressive now (see video below) Google on the other hand decided to build an insanely clunky solution to display 3d maps to avoid using mobile GPUs: A Google server streams (!) a live video of its 3d rendered map to you, the result is a disastrous: a super laggy and clunky 3d view full of video compression artefacts with a response time of 2-3 seconds for every movement And I know WHY they built that, someone felt it was not inclusive to only have 3d maps that are high performing on iOS because Apple's GPUs are insanely fast and can deal with it (as you can see below in Apple Maps) but they wanted to support inferior phones, I get it But then they also decided to worsen the experience for iOS users who could easily run 3d natively on its GPU It's just an insane product decision, there's no way to cut it: they could have super smooth 3d like Apple Maps but neutered it with a clunky live stream Even more insane because Google does have native 3d on iOS in a completely different app that nobody uses: Google Earth Is 3d important? Not rly for nav no but it shows again something about Google's engineering decisions, like the redesign of the Google OAuth Login screen that made zero sense Nobody is speaking up against bad ideas in Google meetings, everyone's too scared of HR maybe, it's the opposite of a meritocracy and it's just super visible from using Google products right now

@levelsio

1,488,855 просмотров • 1 год назад

🎥 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.

🎥 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

2,264,973 просмотров • 1 год назад

In 2024 I rapped on an Ovrkast. beat from For All The Dogs while sitting in my home with absolutely zero expectation of being noticed by anybody. Somehow the freestyle landed on his timeline, he liked it, then unliked it two minutes later like he accidentally touched the screen or something. Cool. Fast forward a couple years and I hit him with an opportunity most underground artists would kill for: access to a feature from an artist 8x as popular than him for only $250. A verse from my homie worth thousands of dollars handed to him on a silver platter. Instead of either taking the play or respectfully declining, he decided to act weird. No response would've been cool. "No thanks" would've been cool. Playing in my face for no reason was corny. I still let it rock. One day later, this man marks my tweet as spam because I answered his rhetorical question with actual logic. That's strike three. I swear some of y'all get a little buzz and immediately develop celebrity syndrome. Suddenly basic respect becomes optional and everybody beneath your follower count is irrelevant. This is why I don't fit in with you high-nose rappers or pretentious producers on the West. The ego be louder than the résumé. You were literally on IG Live making beats with someone who's producing my entire album. This industry is very small. You're 28 years old, bro. Too grown to be moving like the popular kid in homeroom because a few rappers used your beats. Congrats by the way. Keep making beats. That's what you're good at. I respect your work but not your arrogance. But don't mistake my restraint for submission or silence for admiration. Some of y'all got successful before you got mature and it shows.

In 2024 I rapped on an Ovrkast. beat from For All The Dogs while sitting in my home with absolutely zero expectation of being noticed by anybody. Somehow the freestyle landed on his timeline, he liked it, then unliked it two minutes later like he accidentally touched the screen or something. Cool. Fast forward a couple years and I hit him with an opportunity most underground artists would kill for: access to a feature from an artist 8x as popular than him for only $250. A verse from my homie worth thousands of dollars handed to him on a silver platter. Instead of either taking the play or respectfully declining, he decided to act weird. No response would've been cool. "No thanks" would've been cool. Playing in my face for no reason was corny. I still let it rock. One day later, this man marks my tweet as spam because I answered his rhetorical question with actual logic. That's strike three. I swear some of y'all get a little buzz and immediately develop celebrity syndrome. Suddenly basic respect becomes optional and everybody beneath your follower count is irrelevant. This is why I don't fit in with you high-nose rappers or pretentious producers on the West. The ego be louder than the résumé. You were literally on IG Live making beats with someone who's producing my entire album. This industry is very small. You're 28 years old, bro. Too grown to be moving like the popular kid in homeroom because a few rappers used your beats. Congrats by the way. Keep making beats. That's what you're good at. I respect your work but not your arrogance. But don't mistake my restraint for submission or silence for admiration. Some of y'all got successful before you got mature and it shows.

C²

187,452 просмотров • 11 дней назад

This was sent to me a few months ago, reportedly Footage of Chuck Yeager´s NF-104 crash in december 1963, in the Mojave desert. While on testing, jet lost power, went out of control at 108.000 feet. Yeager bailed out at 8500 ft, on the 1st ever emergency ejection in a full pressure, high altitude, flight suit. Many will remember the accident as it appears in the the 1983 movie "The Right Stuff". Looking at such quality footage of such na old event, I thought someone had edited footage from the movie and upscaled with AI. BUT… I was wrong. This is real Footage, although somehow improved. The original Footage is from a Edwards AFB base video, which you can see on the 1st comment, along with an OTD entry. Thanks to Michael Kelly for the help with this one

This was sent to me a few months ago, reportedly Footage of Chuck Yeager´s NF-104 crash in december 1963, in the Mojave desert. While on testing, jet lost power, went out of control at 108.000 feet. Yeager bailed out at 8500 ft, on the 1st ever emergency ejection in a full pressure, high altitude, flight suit. Many will remember the accident as it appears in the the 1983 movie "The Right Stuff". Looking at such quality footage of such na old event, I thought someone had edited footage from the movie and upscaled with AI. BUT… I was wrong. This is real Footage, although somehow improved. The original Footage is from a Edwards AFB base video, which you can see on the 1st comment, along with an OTD entry. Thanks to Michael Kelly for the help with this one

Francisco Cunha

589,592 просмотров • 4 месяцев назад

BREAKING🚨: Video editing just got as simple as editing a text document. Aleph 2.0 is live on Runway's new Edit Studio right now! Here is my quick tutorial showing 3 of its most powerful post-production strengths: Infinite Variations: Swap product colors, change seasons, or update styles—all from the exact same video clip. Zero Wasted Renders: Preview your edit instantly as a static image first to lock in the look before you commit to generating the full video. Multi-Shot Power: Apply an edit once, and watch it propagate automatically across cuts and scene changes without resetting. Stop regenerating from scratch. Grab your own camera roll footage and try it today. 🔗 Try it: > 🎟️ Use code ALEPH2 at checkout for 22% off 2 months of Runway Pro (valid through May 31, 2026) #MadeWithRunway

BREAKING🚨: Video editing just got as simple as editing a text document. Aleph 2.0 is live on Runway's new Edit Studio right now! Here is my quick tutorial showing 3 of its most powerful post-production strengths: Infinite Variations: Swap product colors, change seasons, or update styles—all from the exact same video clip. Zero Wasted Renders: Preview your edit instantly as a static image first to lock in the look before you commit to generating the full video. Multi-Shot Power: Apply an edit once, and watch it propagate automatically across cuts and scene changes without resetting. Stop regenerating from scratch. Grab your own camera roll footage and try it today. 🔗 Try it: > 🎟️ Use code ALEPH2 at checkout for 22% off 2 months of Runway Pro (valid through May 31, 2026) #MadeWithRunway

Arcane Ai

73,066 просмотров • 1 месяц назад

DeepMind just dropped Lyria, a state-of-the-art music generative model. Last year, I said 2022 was the year of pixels and 2023 would be the year of soundwaves. We are making great progress here! The most impressive demo is converting humming to a full instrument suite. I think Lyria will unlock all the operators we are used to in image models: text-based editing, style transfer, in-painting (fill out tracks), out-painting (continue a track), super-resolution, etc. Lyria is deployed as an intuitive software tool to musicians, in partnership with YouTube. This is the right move: ship the model! With enough artists on board, Lyria could spin a data flywheel that learns from the artists' feedback and editing signals. Congrats to DeepMind for shipping! Launch blog:

DeepMind just dropped Lyria, a state-of-the-art music generative model. Last year, I said 2022 was the year of pixels and 2023 would be the year of soundwaves. We are making great progress here! The most impressive demo is converting humming to a full instrument suite. I think Lyria will unlock all the operators we are used to in image models: text-based editing, style transfer, in-painting (fill out tracks), out-painting (continue a track), super-resolution, etc. Lyria is deployed as an intuitive software tool to musicians, in partnership with YouTube. This is the right move: ship the model! With enough artists on board, Lyria could spin a data flywheel that learns from the artists' feedback and editing signals. Congrats to DeepMind for shipping! Launch blog:

Jim Fan

384,184 просмотров • 2 лет назад

VoxCPM 2 just dropped by OpenBMB Only 2B-param open-source TTS (Text-to-Speech) model built for production-grade multilingual voice work. Apache-2.0 license, Can run on only 8GB VRAM. • Eliminates the "robotic" feel of traditional TTS, delivering prosody and emotional depth suitable for high-stakes professional environments like filmmaking, gaming, animation, and audiobooks. • 30-language multilingual: no language tag needed, just type in a supported language and generate directly. • Voice design: create a brand-new voice from a text description alone, like age, tone, pace, or emotion. No reference audio required. Describe the desired voice characteristics (gender, age, tone, emotion, pace …) in Control Instruction, and VoxCPM2 will craft a unique voice from your description alone. • Controllable cloning: clone from a short clip, then steer delivery style without losing the speaker’s core voice. • Ultimate cloning: use reference audio + transcript for continuation-style cloning that keeps the tiny vocal details. • 48kHz output: takes 16kHz reference audio and produces studio-quality speech without an external upsampler. • Real-time ready: around 0.3 RTF on RTX 4090, even lower with Nano-VLLM. • Commercial use: Apache-2.0 licensed. Developer-Friendly Infrastructure: - Native Torch Inference: Direct support for PyTorch-based workflows. - Training Flexibility: Supports both full-parameter and LoRA fine-tuning for specific domain adaptation. - Production Readiness: Compatible with voxcpm-nanovllm for large-scale, high-concurrency deployment.

Rohan Paul

13,541 просмотров • 3 месяцев назад

Interestingly I gave a keynote talk at low carb Denver on March 14th 2020 - it was a blast! Essentially no-one I knew in Ireland, or indeed when I got to Denver, gave a fuck about the hype. The only problem was some people wanted to cancel the event. Myself and a few other smart doctors persuaded the team to go ahead - and we had a great conference - but numbers not amazing because of all the tops-down propaganda going on; people afraid to travel in case it was cancelled etc. In the end I had to get one of the last flights out of the USA, as the tops-down boyos were pulling the plug in lockstep across the world - very impressive operation. Key thing is myself and many others got surreal abuse after running the conf from some successfully propagandized docs - vicious stuff - complete lunacy. We were accused of being murderers essentially. I was learning that a successfully tops-down triggered MF is no joke. That and all the other abuse made me realize that this scam needed to be managed very carefully indeed; hearts and minds and all that...tricky operation from our side, softly softly catchee monkee - as a successfully tops-down triggered MF is no joke 😉 Myself and Tucker discussed this challenge at length in March 2020, with others...and I went with the strategy of calming the horses, acknowledging apparent science, giving some ground.....and opposing mandates and of course, above EVERYTHING, fighting against the tops-down scumbags sinister LOCDOWNS. Here's me April 3rd 2020 with Tucker - in my words, "freedoms-preserving" distancing/masky stuff was the compromise - anything to not get totally cancelled, but rather remain as an effective force against lockdowns. They got their two weeks to flatten the curve, the tops-down scumbaghs - but it was crucial to counter them getting any more: (p.s. note my super-calming tone, think I overdid that tactic maybe...! 😃)

Interestingly I gave a keynote talk at low carb Denver on March 14th 2020 - it was a blast! Essentially no-one I knew in Ireland, or indeed when I got to Denver, gave a fuck about the hype. The only problem was some people wanted to cancel the event. Myself and a few other smart doctors persuaded the team to go ahead - and we had a great conference - but numbers not amazing because of all the tops-down propaganda going on; people afraid to travel in case it was cancelled etc. In the end I had to get one of the last flights out of the USA, as the tops-down boyos were pulling the plug in lockstep across the world - very impressive operation. Key thing is myself and many others got surreal abuse after running the conf from some successfully propagandized docs - vicious stuff - complete lunacy. We were accused of being murderers essentially. I was learning that a successfully tops-down triggered MF is no joke. That and all the other abuse made me realize that this scam needed to be managed very carefully indeed; hearts and minds and all that...tricky operation from our side, softly softly catchee monkee - as a successfully tops-down triggered MF is no joke 😉 Myself and Tucker discussed this challenge at length in March 2020, with others...and I went with the strategy of calming the horses, acknowledging apparent science, giving some ground.....and opposing mandates and of course, above EVERYTHING, fighting against the tops-down scumbags sinister LOCDOWNS. Here's me April 3rd 2020 with Tucker - in my words, "freedoms-preserving" distancing/masky stuff was the compromise - anything to not get totally cancelled, but rather remain as an effective force against lockdowns. They got their two weeks to flatten the curve, the tops-down scumbaghs - but it was crucial to counter them getting any more: (p.s. note my super-calming tone, think I overdid that tactic maybe...! 😃)

Ivor Cummins

10,281 просмотров • 1 год назад

Seedance 2 is out globally on Freepik! 🎸 And now you got to learn how to prompt for it. So I went ahead and made a Spaces workflow for you - link below. And here's a prompt for you to kick off: [STYLE] Ultra-high detail Pixar-quality cinematic animation, 8K, soft global illumination, individual hair and fur strands, realistic fabric simulation, shallow depth of field, warm cozy lighting [FORMAT] 16:9, cinematic multi-shot scene, slow tension build [SCENE] Cozy bedroom at night with strong 80s personality, colorful retro posters on walls, desk with glowing computer, warm lamp. [CHARACTERS] A young man with short dense curly blonde hair forming soft rounded clumps, pale skin, slightly tired blue eyes, wearing a black hoodie A golden retriever with thick light golden fur and expressive eyes. [CAMERA SYSTEM] Smooth cinematic camera, slow push-ins, medium and close shots, no jitter. A scene showing the guy coding. The dog wakes up from some noise. the guy asks what's up. the dog walk to across the room to a closed closet door. noise coming from inside. the guy walks up and gets ready to open the door and calms the dog.

Seedance 2 is out globally on Freepik! 🎸 And now you got to learn how to prompt for it. So I went ahead and made a Spaces workflow for you - link below. And here's a prompt for you to kick off: [STYLE] Ultra-high detail Pixar-quality cinematic animation, 8K, soft global illumination, individual hair and fur strands, realistic fabric simulation, shallow depth of field, warm cozy lighting [FORMAT] 16:9, cinematic multi-shot scene, slow tension build [SCENE] Cozy bedroom at night with strong 80s personality, colorful retro posters on walls, desk with glowing computer, warm lamp. [CHARACTERS] A young man with short dense curly blonde hair forming soft rounded clumps, pale skin, slightly tired blue eyes, wearing a black hoodie A golden retriever with thick light golden fur and expressive eyes. [CAMERA SYSTEM] Smooth cinematic camera, slow push-ins, medium and close shots, no jitter. A scene showing the guy coding. The dog wakes up from some noise. the guy asks what's up. the dog walk to across the room to a closed closet door. noise coming from inside. the guy walks up and gets ready to open the door and calms the dog.

Martin LeBlanc

150,314 просмотров • 3 месяцев назад

Created this race using GPT Image 2 and Seedance 2.0 on TapNow Prompt Follow the storyboard strictly in exact order from Panel 1 to Panel 9. Do not skip, merge, or rearrange scenes. Keep the SAME female cyclist identity across the entire film. No face changes, no hairstyle changes, no helmet changes, no body proportion inconsistencies. Baby pink must remain the dominant apparel color throughout all cycling scenes. Avoid black wardrobe replacements. Preserve realistic nighttime lighting continuity between shots. Maintain the same cool blue tones and subtle red light reflections. Heavy rain intensity must stay visually consistent across all scenes. Water physics must look physically accurate: droplets, splashes, mist, wheel spray, and runoff should behave naturally. Avoid artificial AI motion. Camera movement should feel like real cinema rigs, FPV drones, mounted bike cameras, or stabilized tracking systems. Drone shots must maintain locked framing and smooth movement without random drifting or orbiting. Use subtle cinematic motion only — no excessive shaking or jitter. Keep realistic breathing, body fatigue, pedaling mechanics, and fabric reactions to wind and rain. Preserve shallow depth of field in macro shots and atmospheric haze in wide shots. Keep the environment dark, moody, and cinematic with strong contrast between wet reflections and darkness. Ensure all reflections on asphalt, water droplets, and bike components react naturally to changing light sources. Maintain premium commercial pacing: slow controlled preparation and macro shots transitioning into aggressive high-speed riding sequences. Final output should resemble a high-budget Nike / Rapha night cycling commercial shot during a real mountain storm. Ultra-realistic cinematic night cycling commercial about female endurance cyclists riding through an intense rainstorm in the mountains at night. Premium Nike / Rapha aesthetic with baby pink performance cycling apparel as the dominant accent color. Hyper-realistic documentary look, no stylization, no anime look, no beauty filters. Natural skin texture, realistic rain interaction, physically accurate water behavior, cinematic low-key lighting, cool blue night tones mixed with subtle red rear-light reflections. Heavy rain, fog, wet asphalt reflections, cinematic motion blur, high dynamic range, shallow depth of field, premium sports commercial quality. The film follows a strict 9-panel storyboard structure with seamless cinematic transitions and continuity preserved across every scene. The SAME female cyclist identity must remain consistent throughout the entire video: same face, helmet, glasses, body proportions, baby pink apparel, lighting style, and overall appearance. Maintain continuity of rain intensity, wetness, fog density, and environmental lighting between all shots. Panel 1: Extreme macro close-up of the female cyclist’s eyes and face in heavy rain at night. Focus on soaked eyelashes, wet skin texture, raindrops streaming across the face, baby pink helmet and baby pink face mask visible. Red rear bike light flickers dynamically across her eyes and skin while cool blue night tones dominate the scene. High contrast cinematic lighting, shallow depth of field, subtle breathing motion, intense determined expression. Panel 2: Cinematic medium close-up frontal shot of the cyclist riding aggressively through heavy rain at night. She pedals hard with strong effort and forward-leaning posture. Baby pink waterproof cycling jacket soaked with rainwater. Front bike light cuts through fog and rain with subtle flickering illumination. Wet asphalt reflects red and white lights. Smooth cinematic tracking shot with controlled stable motion and slight natural float. Panel 3: Ultra-realistic macro shot of large raindrops impacting wet asphalt at night. Crown-shaped splashes and overlapping ripples in slow motion. Rough wet asphalt texture, cool blue cinematic tones, subtle reflections from bike lights.

Created this race using GPT Image 2 and Seedance 2.0 on TapNow Prompt Follow the storyboard strictly in exact order from Panel 1 to Panel 9. Do not skip, merge, or rearrange scenes. Keep the SAME female cyclist identity across the entire film. No face changes, no hairstyle changes, no helmet changes, no body proportion inconsistencies. Baby pink must remain the dominant apparel color throughout all cycling scenes. Avoid black wardrobe replacements. Preserve realistic nighttime lighting continuity between shots. Maintain the same cool blue tones and subtle red light reflections. Heavy rain intensity must stay visually consistent across all scenes. Water physics must look physically accurate: droplets, splashes, mist, wheel spray, and runoff should behave naturally. Avoid artificial AI motion. Camera movement should feel like real cinema rigs, FPV drones, mounted bike cameras, or stabilized tracking systems. Drone shots must maintain locked framing and smooth movement without random drifting or orbiting. Use subtle cinematic motion only — no excessive shaking or jitter. Keep realistic breathing, body fatigue, pedaling mechanics, and fabric reactions to wind and rain. Preserve shallow depth of field in macro shots and atmospheric haze in wide shots. Keep the environment dark, moody, and cinematic with strong contrast between wet reflections and darkness. Ensure all reflections on asphalt, water droplets, and bike components react naturally to changing light sources. Maintain premium commercial pacing: slow controlled preparation and macro shots transitioning into aggressive high-speed riding sequences. Final output should resemble a high-budget Nike / Rapha night cycling commercial shot during a real mountain storm. Ultra-realistic cinematic night cycling commercial about female endurance cyclists riding through an intense rainstorm in the mountains at night. Premium Nike / Rapha aesthetic with baby pink performance cycling apparel as the dominant accent color. Hyper-realistic documentary look, no stylization, no anime look, no beauty filters. Natural skin texture, realistic rain interaction, physically accurate water behavior, cinematic low-key lighting, cool blue night tones mixed with subtle red rear-light reflections. Heavy rain, fog, wet asphalt reflections, cinematic motion blur, high dynamic range, shallow depth of field, premium sports commercial quality. The film follows a strict 9-panel storyboard structure with seamless cinematic transitions and continuity preserved across every scene. The SAME female cyclist identity must remain consistent throughout the entire video: same face, helmet, glasses, body proportions, baby pink apparel, lighting style, and overall appearance. Maintain continuity of rain intensity, wetness, fog density, and environmental lighting between all shots. Panel 1: Extreme macro close-up of the female cyclist’s eyes and face in heavy rain at night. Focus on soaked eyelashes, wet skin texture, raindrops streaming across the face, baby pink helmet and baby pink face mask visible. Red rear bike light flickers dynamically across her eyes and skin while cool blue night tones dominate the scene. High contrast cinematic lighting, shallow depth of field, subtle breathing motion, intense determined expression. Panel 2: Cinematic medium close-up frontal shot of the cyclist riding aggressively through heavy rain at night. She pedals hard with strong effort and forward-leaning posture. Baby pink waterproof cycling jacket soaked with rainwater. Front bike light cuts through fog and rain with subtle flickering illumination. Wet asphalt reflects red and white lights. Smooth cinematic tracking shot with controlled stable motion and slight natural float. Panel 3: Ultra-realistic macro shot of large raindrops impacting wet asphalt at night. Crown-shaped splashes and overlapping ripples in slow motion. Rough wet asphalt texture, cool blue cinematic tones, subtle reflections from bike lights.

Sharon Riley

72,716 просмотров • 2 месяцев назад

On Figma Motion, my demo & review. This is one of those updates that clicked swiftly into my workflow. Like in my 3D pipeline, using this stick shift animation, I emphasize hardware feedback with motion from Figma Motion. Assets are animated in Fig Motion and loaded into Blender as video textures for mesh and material control. It's advantageous since it is built into an ubiquitous ecosystem. A lot of work these days start in Figma even for someone like me that works outside the tool frequently. Can't over-emphasize my appreciation for the schema used to introduce motion to nearly all properties. Reminds me of how motion works in Blender - with better complexity management. Better than introducing more menus for those. Ease curves iD between keyframes is also an improvement over existing systems. Having spent some time on the tool, here are updates I'll like to see to Figma Motion. These are based on my immediate needs as at the time of working on this demo: • Using modifier keys (CMD, Shift, Ctrl) to jump / nudge across the timeline. E.g: holding down Shift key to make the playhead jump 100ms etc. • Jump to previous or next keyframe. • Better anchor point trails • Renaming layers from the timeline as well. • Editable custom bezier styles: after saving a style, I should be able to edit the curve - just as you can edit colour styles. • Enable transform on the timeline. I should be able to flip or scale keyframes. I hope to continue trying more ideas. Craft focused tools have had to take a backseat in recent times. Pleasing to see this come to light.

On Figma Motion, my demo & review. This is one of those updates that clicked swiftly into my workflow. Like in my 3D pipeline, using this stick shift animation, I emphasize hardware feedback with motion from Figma Motion. Assets are animated in Fig Motion and loaded into Blender as video textures for mesh and material control. It's advantageous since it is built into an ubiquitous ecosystem. A lot of work these days start in Figma even for someone like me that works outside the tool frequently. Can't over-emphasize my appreciation for the schema used to introduce motion to nearly all properties. Reminds me of how motion works in Blender - with better complexity management. Better than introducing more menus for those. Ease curves iD between keyframes is also an improvement over existing systems. Having spent some time on the tool, here are updates I'll like to see to Figma Motion. These are based on my immediate needs as at the time of working on this demo: • Using modifier keys (CMD, Shift, Ctrl) to jump / nudge across the timeline. E.g: holding down Shift key to make the playhead jump 100ms etc. • Jump to previous or next keyframe. • Better anchor point trails • Renaming layers from the timeline as well. • Editable custom bezier styles: after saving a style, I should be able to edit the curve - just as you can edit colour styles. • Enable transform on the timeline. I should be able to flip or scale keyframes. I hope to continue trying more ideas. Craft focused tools have had to take a backseat in recent times. Pleasing to see this come to light.

seyi

28,836 просмотров • 23 дней назад

Charlie Kirk was murdered by professional hitmen and the FBI blamed a patsy. Nothing about this assassination makes any sense, Amateur Shooter Skill Discrepancy: The official narrative claims Tyler Robinson, with no professional training, executed a precise 142-yard neck shot using a vintage Mauser 98 rifle. Ballistics data shows a miniscule success rate for novices. He had zero practice records or ammo traces. single-shot perfection is impossible without expert help. Invisible Rooftop Presence and Firing: No eyewitnesses saw Robinson climbing, positioning, or shooting despite ~3,000 attendees and the rooftop visible in daylight. Witness statements point to conflicting shot directions. The probability of zero sightings 2 minutes Video shows a fleeing figure, but actions exceed feasible time for an amateur. Post-Escape Behavior: Calm demeanor post-shot he was at Dairy Queen posting Discord memes. Only arrested after dad's tip-off. His "Confession" text to vanished lover, unreleased geo-tracking data, amateur would show panic, not casual behavior. Audio Discrepancy across Multiple Sources: Videos show varying shot sounds (immediate crack in close views, delays/echoes in others). Physics predicts consistent crack-bang from a single rooftop. Variations imply closer/suppressed weapon or multiple shooters. Trajectory and Wound Mismatches: Blood spray arcs forward/left, not downward from elevated shot. No exit despite high velocity. Some Witnesses report "two shots." Evidence Tampering and Scene Handling: Stage/cameras dismantled ~5-10 mins post-shot. FBI delayed ~16 mins and no autopsy was released. Videos show staff yanking SD cards, there are gag orders on witnesses and the scene was trampled by people who were supposed to be professionals. Pre-Event Foreknowledge Indicators: Google searches for "Tyler Robinson" spiked pre-shot. Hand signals in videos, scrubbed CIA-linked professors. Absurd.

Charlie Kirk was murdered by professional hitmen and the FBI blamed a patsy. Nothing about this assassination makes any sense, Amateur Shooter Skill Discrepancy: The official narrative claims Tyler Robinson, with no professional training, executed a precise 142-yard neck shot using a vintage Mauser 98 rifle. Ballistics data shows a miniscule success rate for novices. He had zero practice records or ammo traces. single-shot perfection is impossible without expert help. Invisible Rooftop Presence and Firing: No eyewitnesses saw Robinson climbing, positioning, or shooting despite ~3,000 attendees and the rooftop visible in daylight. Witness statements point to conflicting shot directions. The probability of zero sightings 2 minutes Video shows a fleeing figure, but actions exceed feasible time for an amateur. Post-Escape Behavior: Calm demeanor post-shot he was at Dairy Queen posting Discord memes. Only arrested after dad's tip-off. His "Confession" text to vanished lover, unreleased geo-tracking data, amateur would show panic, not casual behavior. Audio Discrepancy across Multiple Sources: Videos show varying shot sounds (immediate crack in close views, delays/echoes in others). Physics predicts consistent crack-bang from a single rooftop. Variations imply closer/suppressed weapon or multiple shooters. Trajectory and Wound Mismatches: Blood spray arcs forward/left, not downward from elevated shot. No exit despite high velocity. Some Witnesses report "two shots." Evidence Tampering and Scene Handling: Stage/cameras dismantled ~5-10 mins post-shot. FBI delayed ~16 mins and no autopsy was released. Videos show staff yanking SD cards, there are gag orders on witnesses and the scene was trampled by people who were supposed to be professionals. Pre-Event Foreknowledge Indicators: Google searches for "Tyler Robinson" spiked pre-shot. Hand signals in videos, scrubbed CIA-linked professors. Absurd.

Nacho Business

33,742 просмотров • 8 месяцев назад

These glasses are magic Nano Banana 2 + Seedance 2.0 on BudgetPixel AI prompt Cinematic realistic 15-second live-action scene of a charming first date at an upscale outdoor garden cafe under large shady trees with warm string lights overhead. Photorealistic, high production value, filmic color grade. A handsome man in his mid-30s (dark wavy hair, light stubble, blue eyes, charming smile) wearing a rich brown short-sleeve polo shirt and white pants sits across from a beautiful Western woman in her mid-20s (long wavy blonde hair, expressive face, natural makeup) wearing a cream sleeveless ribbed top with black trim. Start with a medium over-the-shoulder shot from behind the man. The woman asks playfully but skeptically: “So what do you actually do? Please don’t say entrepreneur.” Cut to tight close-up on the man as he smiles confidently and replies: “Well, I flip vintage furniture, and I do some design consulting on the side.” He holds a white coffee cup. Quick reaction close-up on the woman, eyebrows slightly furrowed: “Like chairs?” He answers warmly: “Yeah, people pay a lot for chairs.” Her expression transforms — doubt melts into amusement and attraction. She smiles, looks down shyly then back up at him and says playfully: “Okay, I think I’m actually gonna head out.” Natural dappled sunlight filtering through dense green tree leaves, warm glowing string lights, shallow depth of field with creamy bokeh, rich earthy color palette (chocolate brown, cream, warm beige, lush greens), soft cinematic lighting, flattering skin tones, subtle film grain, intimate and romantic atmosphere, high detail, photorealistic, shot on 35mm film, premium commercial quality like high-end dating app ads.

These glasses are magic Nano Banana 2 + Seedance 2.0 on BudgetPixel AI prompt Cinematic realistic 15-second live-action scene of a charming first date at an upscale outdoor garden cafe under large shady trees with warm string lights overhead. Photorealistic, high production value, filmic color grade. A handsome man in his mid-30s (dark wavy hair, light stubble, blue eyes, charming smile) wearing a rich brown short-sleeve polo shirt and white pants sits across from a beautiful Western woman in her mid-20s (long wavy blonde hair, expressive face, natural makeup) wearing a cream sleeveless ribbed top with black trim. Start with a medium over-the-shoulder shot from behind the man. The woman asks playfully but skeptically: “So what do you actually do? Please don’t say entrepreneur.” Cut to tight close-up on the man as he smiles confidently and replies: “Well, I flip vintage furniture, and I do some design consulting on the side.” He holds a white coffee cup. Quick reaction close-up on the woman, eyebrows slightly furrowed: “Like chairs?” He answers warmly: “Yeah, people pay a lot for chairs.” Her expression transforms — doubt melts into amusement and attraction. She smiles, looks down shyly then back up at him and says playfully: “Okay, I think I’m actually gonna head out.” Natural dappled sunlight filtering through dense green tree leaves, warm glowing string lights, shallow depth of field with creamy bokeh, rich earthy color palette (chocolate brown, cream, warm beige, lush greens), soft cinematic lighting, flattering skin tones, subtle film grain, intimate and romantic atmosphere, high detail, photorealistic, shot on 35mm film, premium commercial quality like high-end dating app ads.

Sharon Riley

54,351 просмотров • 13 дней назад