Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Photorealistic 4K scene of rectangular ice frames scattered across a frozen winter bay at dusk, each transparent ice frame capturing different gradients of the blue-to-orange sunset sky, some standing upright in ice sheets, others half-submerged in dark water with perfect reflections, National Geographic quality lighting with deep blues transitioning to warm golds, hyperreal ice textures, landscape format with bold ‘Images’ text overlay, serene atmospheric depth, no CGI glow, natural documentary aesthetic.
A New AI Video Model From ByteDance is Making Waves | PetaPixel https://petapixel.com/2026/02/09/bytedance-seedance-2-ai-video/
Bytedance shows impressive progress in AI video with Seedance 2.0 https://the-decoder.com/bytedance-shows-impressive-progress-in-ai-video-with-seedance-2-0/
ByteDance’s Seedance 2.0: “”Monica’s apartment from the show Friends, except all of the friends are otters wearing wigs. The otter with a Rachel wig says “”Is anything weird”” and the one with a Joey wig says “”Nope, all is normal”””” Huh.”” https://x.com/emollick/status/2021411069865099764
Example of Seedance with some consistency issues, but still: “”Action sequence shot for a big budget action movie where two elegantly dressed woman on giant snails race slowly around a track as gunners on the snails fire at each other. Lots of quick cuts and action movie cliches”””” https://x.com/emollick/status/2021432517992280127
I literally cannot get enough of those clips. SeeDance solved the touring-test for text2video.”” https://x.com/kimmonismus/status/2021605142580412558
Runway’s $5.3B valuation fuels world models | The Deep View https://www.thedeepview.com/articles/runway-s-usd5-3b-valuation-fuels-world-models
seedance 2.0 has passed the uncanny valley for me it’s so good, i wanna see what kind of dataset is it trained on?”” https://x.com/maharshii/status/2021549823321886755
SeeDance 2.0: “”An anime where an otter goes into a large mech, with lots of quick shots of mechanical parts and gears turning. The otter gives a grim thumbs up, and then pilots the mech, flying into battle against an octopus made of marble.”” Again, this was the very first try”” https://x.com/emollick/status/2021412306291392535
Seedance: “”A documentary about how otters view Ethan Mollick’s “”Otter Test”” which judges AIs by their ability to create images of otters sitting in planes”” Again, first result.”” https://x.com/emollick/status/2021425594664353963
Seedance: “”An influencer in a TikTok video wearing an otter baseball cap showing off the weird swirling vortex they have in their living room. Cheese shoots out of the vortex every few seconds, forcing them to move around the room”” Again, very first attempt.”” https://x.com/emollick/status/2021419361039462520
The new ByteDance SeeDance 2.0 video model is VERY good. This is the very first output from my very first prompt: “”A nature documentary about an otter flying an airplane”””” https://x.com/emollick/status/2021409874832392508
China on a coordinated offensive — dropping Kling 3.0 and now Seedance 2.0, while we’re still debating release cycles for Sora and Veo. This is an insane leap in cinematic realism — dare I say the nano banana moment for video is here.”” https://x.com/bilawalsidhu/status/2020943565904330933
I’ve just received access to SeeDance2. Very first test and it really does live up to its hype. This is a slow and considered generation but it is very, very cool. Down with a virus right now, but I’ll enjoy testing this.”” https://x.com/TomLikesRobots/status/2021347131500667316
Interesting thread from @venturetwins on China winning the AI video race. Having spent years building in AI video, here’s how I see it: The gap isn’t about talent or compute. It’s structural. Chinese models train without IP constraints. Western ones can’t. That’s it. Seedance”” https://x.com/brivael/status/2021657223206724073
Seedance 2.0 beats Google’s Veo 3.1 on my video gen reasoning task. It generates 5 coherent tic tac toe moves in a row before breaking down. Veo only manages 1 or 2 h/t @janekm for seedancing for me :)”” https://x.com/paul_cal/status/2021657394166870507
short writeup today, not much to say until tech report. also feel uneasy about how shady seedance seems to be, either its fake or they have the worst PR team in AI”” https://x.com/swyx/status/2021500688010969216
A cartoonist’s review of AI art – The Oatmeal https://theoatmeal.com/comics/ai_art
🚀 Introducing Qwen-Image-2.0 — our next-gen image generation model! 🎨 Your imagination, unleashed. ✨ Type a paragraph → get a pro slides ✨ Describe a scene → get photoreal 2K magic ✨ Add text → it just works (no more glitchy letters!) ✨ Key upgrades: ✅ Professional”” https://x.com/Alibaba_Qwen/status/2021137577311600949
A quick update — we’ve fixed a Qwen-Image 2.0 bug in Qwen Chat that impacted: • Classical Chinese poem ordering in image generation • Character consistency during image editing ✅Patch is live now! https://t.co/DWnxVxa0hY Go test it out and drop us your feedback.”” https://x.com/Alibaba_Qwen/status/2021510747671720368
Folks ask about training an RLM like a hypothetical. In the paper, we do post-train and release open-weights RLM-Qwen3-8B-v0.1 on HF. It’s a tiny proof of concept, but it was surprisingly easy to get a marked jump in capability. Maybe learning to recurse is not too hard for 8B.”” https://x.com/lateinteraction/status/2020877152854409691
https://t.co/DIetNHHMp3 Qwen3.5 architecture is out: A vision language model, hybrid SSM-Transformer using Gated DeltaNet linear attention mixed with standard attention, interleaved MRoPE, and shared+routed MoE experts.”” https://x.com/QuixiAI/status/2021109801606893837
Kimi K2‑0905 and Qwen3‑Max preview: two 1T open weights models launched | AINews https://news.smol.ai/issues/25-09-05-1t-models
Qwen https://qwen.ai/blog?id=a6f483777144685d33cd3d2af95136fcbeb57652&from=research.research-list
Qwen https://qwen.ai/blog?id=qwen-image-2.0
Qwen https://qwen.ai/blog?id=qwen-image-layered
Qwen-Image: SOTA text rendering + 4o-imagegen-level Editing Open Weights MMDiT | AINews https://news.smol.ai/issues/25-08-04-qwen-image
Leave a Reply