Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Announcing Artificial Analysis Video Arena - the first crowdsourced comparison for Text to Video models Text to Video models are accelerating rapidly and crossing quality thresholds every month. We created Video Arena to compare them using the only source of truth for visual media - human preference! Video Arena...

ArtificialAnlys's profile picture

Artificial Analysis

122,095 subscribers

27,108 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildungFinanzen
LIVE

Anya Rossi• Live Now

Private livecam show

8 Kommentare

Profilbild von Artificial Analysis
Artificial Analysisvor 1 Jahr

Contribute to the Video Arena! 🔗

Profilbild von Simon Smith
Simon Smithvor 1 Jahr

Does it account for generation time or just quality?

Profilbild von Artificial Analysis
Artificial Analysisvor 1 Jahr

Just quality for the Arena this week but we'll we back soon with full performance and cost coverage

Profilbild von Tristan Rhodes
Tristan Rhodesvor 1 Jahr

Yes! I love seeing your team expand the areas you cover. :)

Profilbild von Andrew Arkins
Andrew Arkinsvor 1 Jahr

Great idea!

Profilbild von David Hendrickson
David Hendricksonvor 1 Jahr

This is great to see! I've looked at but their models don't seem to update very often so its nice to see another alternative to compare these text to video sources.

Profilbild von Prashant
Prashantvor 1 Jahr

genAI is incomplete without video. this is great to see that your team is putting effort in bringing transparent analysis of the popular tools

Profilbild von Alfred Rotors
Alfred Rotorsvor 1 Jahr

I was wondering when you would do this - fantastic! I’ll definitely give this a go.

Ähnliche Videos

Grok Imagine Video is now dominating the Artificial Analysis Arena #1 in both Text→Video and Image→Video Outranking Veo 3.1, Sora 2 and Kling 2.6 Pro in every way - Best overall quality - Fastest generation times - Lowest cost-to-performance ratio - Native audio-video support xAI is leading the next wave of AI video generation
0:30

Grok Imagine Video is now dominating the Artificial Analysis Arena #1 in both Text→Video and Image→Video Outranking Veo 3.1, Sora 2 and Kling 2.6 Pro in every way - Best overall quality - Fastest generation times - Lowest cost-to-performance ratio - Native audio-video support xAI is leading the next wave of AI video generation

X Freeze

16,972 Aufrufe • vor 6 Monaten

Runway released Gen-4.5 today and it is already ranked first on the Video Arena leaderboard. We sat down with CEO Cristóbal Valenzuela to discuss how a small team is currently beating Google and Meta in the race for state-of-the-art video generation. The full episode is below!
1:08

Runway released Gen-4.5 today and it is already ranked first on the Video Arena leaderboard. We sat down with CEO Cristóbal Valenzuela to discuss how a small team is currently beating Google and Meta in the race for state-of-the-art video generation. The full episode is below!

Weights & Biases

367,588 Aufrufe • vor 8 Monaten

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."
7:17

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."

MTS

55,187 Aufrufe • vor 12 Tagen

Are open source models catching up to proprietary models? We’ve looked back at 3 years of Arena’s data to show how the race has evolved. For comparison, we’ve taken the top 20% of the models and uncovered the following: - Before mid 2024: The gap was between 100-150 points - In the second half of 2024, the gap rapidly narrowed to ~50 points - This was driven by the fact that proprietary models have not significantly improved between early 2023 and November 2024 - hovering around the 1350 score for the top 20% of proprietary models - Then since Jan 2025, we saw a parallel improvement in both proprietary and open source models - Meaning that for the last ~14 months the gap stayed steady at around 50-60 points For context, 50 points is the gap between the 1st and 20th place in the Overall leaderboard Today, proprietary models take up the first 20 spots on the Text Arena, with Anthropic, Google DeepMind , xAI and OpenAI leading in the rankings. The top open source models are ranked #20 (GLM-5 by Z.ai ), #23 (Kimi-K2.5-Thinking by Kimi.ai ) and #27 (Qwen3.5-397b-a17b by Qwen ).
0:21

Are open source models catching up to proprietary models? We’ve looked back at 3 years of Arena’s data to show how the race has evolved. For comparison, we’ve taken the top 20% of the models and uncovered the following: - Before mid 2024: The gap was between 100-150 points - In the second half of 2024, the gap rapidly narrowed to ~50 points - This was driven by the fact that proprietary models have not significantly improved between early 2023 and November 2024 - hovering around the 1350 score for the top 20% of proprietary models - Then since Jan 2025, we saw a parallel improvement in both proprietary and open source models - Meaning that for the last ~14 months the gap stayed steady at around 50-60 points For context, 50 points is the gap between the 1st and 20th place in the Overall leaderboard Today, proprietary models take up the first 20 spots on the Text Arena, with Anthropic, Google DeepMind , xAI and OpenAI leading in the rankings. The top open source models are ranked #20 (GLM-5 by Z.ai ), #23 (Kimi-K2.5-Thinking by Kimi.ai ) and #27 (Qwen3.5-397b-a17b by Qwen ).

Arena.ai

22,447 Aufrufe • vor 4 Monaten

Video Model Comparison: Image to video I updated an older comparison with a new image and prompt to test in several models: • Pika 2.2 • PixVerse 4 • Runway Gen-4 • Google Veo 3 • OpenAI Sora • Kling 2.1 Pro • Luma Ray2 • Hailuo I2V I used the same prompt and Midjourney image in each model 2-3 times and chose my favorite results below:
1:12

Video Model Comparison: Image to video I updated an older comparison with a new image and prompt to test in several models: • Pika 2.2 • PixVerse 4 • Runway Gen-4 • Google Veo 3 • OpenAI Sora • Kling 2.1 Pro • Luma Ray2 • Hailuo I2V I used the same prompt and Midjourney image in each model 2-3 times and chose my favorite results below:

Heather Cooper

98,406 Aufrufe • vor 1 Jahr

🎬 Video Model Comparison: Text to video • Google Veo 2 • OpenAI Sora • Hunyuan Video • Pika 2.1 • Alibaba Wanx 2.1 • Runway Gen-3 • Kling 1.6 • Luma Ray2 • Hailuo T2V-01 I used the same prompt on each model for 2 generations and chose the best results below. Prompt: A majestic white tiger prowling silently through a dense jungle, sunlight piercing through the foliage to illuminate its fur; shot with a telephoto lens for depth, using soft natural lighting and creating a mysterious yet tranquil atmosphere. Prompt credit: LudovicCreator Overall, the results are impressive for each one. We have many choices for AI video! I could have tested more models, but this visual is crowded enough. Drop your results in the comments 👇
1:02

🎬 Video Model Comparison: Text to video • Google Veo 2 • OpenAI Sora • Hunyuan Video • Pika 2.1 • Alibaba Wanx 2.1 • Runway Gen-3 • Kling 1.6 • Luma Ray2 • Hailuo T2V-01 I used the same prompt on each model for 2 generations and chose the best results below. Prompt: A majestic white tiger prowling silently through a dense jungle, sunlight piercing through the foliage to illuminate its fur; shot with a telephoto lens for depth, using soft natural lighting and creating a mysterious yet tranquil atmosphere. Prompt credit: LudovicCreator Overall, the results are impressive for each one. We have many choices for AI video! I could have tested more models, but this visual is crowded enough. Drop your results in the comments 👇

Heather Cooper

255,567 Aufrufe • vor 1 Jahr

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

⚡AI Video Model Comparison: Text to Video 9 Models included: • Google Veo 2 • Adobe Firefly Video • Hunyuan Video • Pika 2.1 Turbo • Genmo Mochi 1 • Runway Gen-3 • Kling 1.6 • Luma Ray2 •.Hailuo T2V-01 Director I used the same prompt on each model x 2 generations and chose my favorite results. Prompt: [Tilt up, Left circling] From the base of an ancient pyramid as storm clouds gather, lightning illuminating hieroglyphics. [Zoom out] Sand swirls in the wind. Epic scale, dramatic lighting. Overall, the results are interesting and dramatic. I don't have a favorite, but you might!
1:11

⚡AI Video Model Comparison: Text to Video 9 Models included: • Google Veo 2 • Adobe Firefly Video • Hunyuan Video • Pika 2.1 Turbo • Genmo Mochi 1 • Runway Gen-3 • Kling 1.6 • Luma Ray2 •.Hailuo T2V-01 Director I used the same prompt on each model x 2 generations and chose my favorite results. Prompt: [Tilt up, Left circling] From the base of an ancient pyramid as storm clouds gather, lightning illuminating hieroglyphics. [Zoom out] Sand swirls in the wind. Epic scale, dramatic lighting. Overall, the results are interesting and dramatic. I don't have a favorite, but you might!

Heather Cooper

80,297 Aufrufe • vor 1 Jahr

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

3,525,190 Aufrufe • vor 2 Monaten

GPT-5.2-high by OpenAI is off to a strong start in the Code Arena. ⚡️ If you’re new here: Code Arena is where AI models build full web apps, tools, and interactive sites — all from a single prompt. Watch the video to see GPT-5.2-high in action, then try your own prompt and reply with your creation below. ⬇️
1:24

GPT-5.2-high by OpenAI is off to a strong start in the Code Arena. ⚡️ If you’re new here: Code Arena is where AI models build full web apps, tools, and interactive sites — all from a single prompt. Watch the video to see GPT-5.2-high in action, then try your own prompt and reply with your creation below. ⬇️

Arena.ai

246,337 Aufrufe • vor 8 Monaten

🚨BIG NEWS: 🎬 Video Arena is now live on the web! Test out Veo 3.1, Sora 2, Seedance v1.5 Pro, Kling 2.6 Pro, Wan 2.5 & more. What started last summer as a small Discord bot experiment has grown into a rigorous way to measure and understand how frontier video models perform with real-world use. Thank you to our wonderful community for all the feedback! Today, we’re opening up access by making it available on the web. 🎥 Generate videos with 15 different frontier AI models and compare them head-to-head. 📊 Vote for the best output to power the leaderboards.
0:30

🚨BIG NEWS: 🎬 Video Arena is now live on the web! Test out Veo 3.1, Sora 2, Seedance v1.5 Pro, Kling 2.6 Pro, Wan 2.5 & more. What started last summer as a small Discord bot experiment has grown into a rigorous way to measure and understand how frontier video models perform with real-world use. Thank you to our wonderful community for all the feedback! Today, we’re opening up access by making it available on the web. 🎥 Generate videos with 15 different frontier AI models and compare them head-to-head. 📊 Vote for the best output to power the leaderboards.

Arena.ai

62,645 Aufrufe • vor 6 Monaten

Bytedance is dropping the best video gen model in the world in early July: Seedance 2.5! The video below (audio on) is the launch video from their Volcano Engine conference this week. It cements China’s absolute dominance in video. — 2x’d generation length of all previous models to 30s, with audio + 4k video — >5x’d reference images / audio / video to 50 — Allows localized editing (specific characters, closing, detail), will come with copyright filter Seedance 2 is already the #1 video model and does a whopping $2B in ARR, in a mere 4.5mos! At the current pricing of $2.5/15s, that implies >3.3M hours of video (!) have been generated. That’s 3x every feature film ever made and dozens of Netflixes. Only 3 US AI startups make more revenue. We are 2x’ing realistic video gen length every 6mos. — May 2025: Veo 3 does audio + video for the first time, 15s — Jan 2026: Kling 3 does 15s — Feb 2026: Seedance 2 does 15s, big quality bump — July 2026: 2.5 will do 30s In 18mos, entire music videos will be oneshotted by AI. China continues to extend its lead on video models vs America.
2:12

Bytedance is dropping the best video gen model in the world in early July: Seedance 2.5! The video below (audio on) is the launch video from their Volcano Engine conference this week. It cements China’s absolute dominance in video. — 2x’d generation length of all previous models to 30s, with audio + 4k video — >5x’d reference images / audio / video to 50 — Allows localized editing (specific characters, closing, detail), will come with copyright filter Seedance 2 is already the #1 video model and does a whopping $2B in ARR, in a mere 4.5mos! At the current pricing of $2.5/15s, that implies >3.3M hours of video (!) have been generated. That’s 3x every feature film ever made and dozens of Netflixes. Only 3 US AI startups make more revenue. We are 2x’ing realistic video gen length every 6mos. — May 2025: Veo 3 does audio + video for the first time, 15s — Jan 2026: Kling 3 does 15s — Feb 2026: Seedance 2 does 15s, big quality bump — July 2026: 2.5 will do 30s In 18mos, entire music videos will be oneshotted by AI. China continues to extend its lead on video models vs America.

Deedy

70,213 Aufrufe • vor 1 Monat

if you want to make money fast right now: - take $500 to buy AI credits (borrow if needed) - become insanely good at all ai video tools (zora 2, veo3, klingt, runway ml, midjourney etc) - study legendary video ads/launch videos - specialize in creating ai launch videos for startups with vc funding - study people like PJ Ace (get on his NL!!) - to get your first clients, create videos on X for these companies and tag them (the more unconventional the better) - you can get from 0 to 10k+ month in 30-60 days imo the demand is off the charts the ai video models are getting better at an insane speed (way faster than the text generation models) generational opportunity for young people right now
2:13

if you want to make money fast right now: - take $500 to buy AI credits (borrow if needed) - become insanely good at all ai video tools (zora 2, veo3, klingt, runway ml, midjourney etc) - study legendary video ads/launch videos - specialize in creating ai launch videos for startups with vc funding - study people like PJ Ace (get on his NL!!) - to get your first clients, create videos on X for these companies and tag them (the more unconventional the better) - you can get from 0 to 10k+ month in 30-60 days imo the demand is off the charts the ai video models are getting better at an insane speed (way faster than the text generation models) generational opportunity for young people right now

Ole Lehmann

170,224 Aufrufe • vor 10 Monaten

💄AI Video Model Comparison: Text to Video 10 Models included: • Google Veo2 • Adobe Firefly Video • Hunyuan Video • Pika 2.1 • Wan-2.1 • Runway Gen-3 • Kling AI 1.6 • Luma Ray2 • Hailuo MiniMax • Sora (not on grid, but in the full video) I used the same prompt on each model x 4 generations and chose my favorite results below. ⭕ Prompt: A person stands in a bright, airy room, bathed in soft natural light streaming through a large window adorned with sheer white curtains. As they gaze into a shimmering mirror, their hand, elegantly manicured with a deep crimson polish, lifts a glossy lip applicator towards their lips. Their outfit, a flowing pastel blouse paired with chic high-waisted trousers, exudes effortless style, complemented by delicate gold jewelry that sparkles subtly in the light. Applying lipstick, lip gloss, or any makeup seems to be extremely difficult for AI video models. It was hard to get a usable result for many of these. This prompt was generated on Nim with the Video Describe feature, and it worked better than my original prompt. Let me know what you think of the results!
1:10

💄AI Video Model Comparison: Text to Video 10 Models included: • Google Veo2 • Adobe Firefly Video • Hunyuan Video • Pika 2.1 • Wan-2.1 • Runway Gen-3 • Kling AI 1.6 • Luma Ray2 • Hailuo MiniMax • Sora (not on grid, but in the full video) I used the same prompt on each model x 4 generations and chose my favorite results below. ⭕ Prompt: A person stands in a bright, airy room, bathed in soft natural light streaming through a large window adorned with sheer white curtains. As they gaze into a shimmering mirror, their hand, elegantly manicured with a deep crimson polish, lifts a glossy lip applicator towards their lips. Their outfit, a flowing pastel blouse paired with chic high-waisted trousers, exudes effortless style, complemented by delicate gold jewelry that sparkles subtly in the light. Applying lipstick, lip gloss, or any makeup seems to be extremely difficult for AI video models. It was hard to get a usable result for many of these. This prompt was generated on Nim with the Video Describe feature, and it worked better than my original prompt. Let me know what you think of the results!

Heather Cooper

61,177 Aufrufe • vor 1 Jahr

🎥 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

2,265,399 Aufrufe • vor 1 Jahr

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 1 Jahr

📢 Introducing DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models Compared to vanilla DPO, we improve paired data construction and preference label granularity, leading to better visual quality and motion strength with only 1/3 of the data. 🧵
0:48

📢 Introducing DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models Compared to vanilla DPO, we improve paired data construction and preference label granularity, leading to better visual quality and motion strength with only 1/3 of the data. 🧵

Ziyi Wu

35,514 Aufrufe • vor 1 Jahr

🎬 Video is now live on Runware! Run top models like SeeDance 1.0, Hailuo 02, Veo 3, Kling 2.1 — at the lowest price per video. On average 35% cheaper than anyone else. To celebrate, get $10 free credit and up to $250K in bonuses for high volume. 🧵👇
0:31

🎬 Video is now live on Runware! Run top models like SeeDance 1.0, Hailuo 02, Veo 3, Kling 2.1 — at the lowest price per video. On average 35% cheaper than anyone else. To celebrate, get $10 free credit and up to $250K in bonuses for high volume. 🧵👇

Runware

736,451 Aufrufe • vor 1 Jahr

The improvement in AI-generated videos over the past 15-16 months is remarkable. The first video was released in March or April 2023, while the second video came out in August 2024. The progress is immense, and it's expected to continue in the coming year. Some of the best AI video tools right now include: - Gen-3 Alpha - Kling AI - Luma Labs - Sora (OpenAI, not yet available for everyone)
0:25

The improvement in AI-generated videos over the past 15-16 months is remarkable. The first video was released in March or April 2023, while the second video came out in August 2024. The progress is immense, and it's expected to continue in the coming year. Some of the best AI video tools right now include: - Gen-3 Alpha - Kling AI - Luma Labs - Sora (OpenAI, not yet available for everyone)

AshutoshShrivastava

1,865,204 Aufrufe • vor 2 Jahren

We’re unveiling a new look for Artificial Analysis! We’ve come a long way since launching Artificial Analysis over 2 years ago. Today, we benchmark 400+ models, 50+ inference providers, and benchmark not only language models but also image, video, speech, music, hardware, and agents. Our mission to support the AI ecosystem with independent benchmarking remains the same, but our brand and website refresh is designed to better reflect how much we’ve grown and how much further we plan to go. A huge thank you to everyone who has been part of the Artificial Analysis community along the way: from developers choosing models and building agents, to labs, inference and hardware providers, and fellow independent researchers.
0:25

We’re unveiling a new look for Artificial Analysis! We’ve come a long way since launching Artificial Analysis over 2 years ago. Today, we benchmark 400+ models, 50+ inference providers, and benchmark not only language models but also image, video, speech, music, hardware, and agents. Our mission to support the AI ecosystem with independent benchmarking remains the same, but our brand and website refresh is designed to better reflect how much we’ve grown and how much further we plan to go. A huge thank you to everyone who has been part of the Artificial Analysis community along the way: from developers choosing models and building agents, to labs, inference and hardware providers, and fellow independent researchers.

Artificial Analysis

18,159 Aufrufe • vor 4 Monaten