Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.
If you arrived here through a search or shared link, this page collects the links I found for Video for the week ending August 7, 2026.
As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.
This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Gemini 3.1 Flash Image Preview.
Category Cover Image Prompt: A small weathered drive-in movie screen standing at the far edge of a mirror-still marsh pond at night, its blank face catching only faint starlight and reflecting perfectly in the dark glassy water among slate reeds, under a vast indigo sky dense with stars and a thin mist low across the water, painterly nocturne in the style of American Tonalism and Luminism with deep blues, muted marsh greens, reed golds, generous negative space in the upper sky for a bold title, low horizon, quiet contemplative mood.
This Week in Video News
Summary by Claude Sonnet 5.5 based on this week’s links:
- FLUX 3 Video launches: Black Forest Labs released its first video model, with native audio, clips up to 20 seconds on fal, multilingual dialogue and video continuation. A Draft mode is meant for fast, cheaper exploration.
- MiniMax H3 leads open video: MiniMax-H3 open weights came out with ComfyUI nodes, and Arena reported it as the top open model in text-to-video and image-to-video. Simon Willison ran it on an M5 Pro Mac: a ~115GB download and about 45 minutes for one clip.
- World models are the research buzz: Several posts pointed to video world models, including a computer-graphics dataset proposed for training them and Decart's Anywear, which lets agents show products inside your own world. One poster called it the summer of world models.
This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.
This week's links related to Video
Seedance 2.5 is the Fable of video generation models. By far the priciest, but clearly the leader of the pack.”
https://x.com/bilawalsidhu/status/2083681664333476044
I asked Fable 5 to make me a lyric video full video on yt”
https://x.com/jeffgwoah/status/2075243582378631287
I had Fable build a working Rothko-inspired city builder based on the fake AI video I created a year ago. This time, the unique mechanic the AI developed is that you play with the margins between colors & forms to grow your city Neat! Its pretty relaxing:
https://x.com/emollick/status/2083240237774385461
This time Fable built me the Van Gogh city building game that I faked in an AI video last year. The key mechanic the AI came up with is painting the landscape with big brushstrokes & an environment that evolves with weather and seasons. Chill and pretty:
https://x.com/emollick/status/2084826713922355207
FLUX 3 Video is here. Serious, fun, creative, real, cinematic, whatever you need it to be. Native audio, Text to Video, Image to Video with multiple frames, video continuation, dialogue in multiple languages. Comes with Draft mode so you can explore ideas fast at a fraction of”
https://x.com/bfl_ai/status/2084693191484469305
FLUX 3 by @bfl_ai is now available on fal. Up to 20s per generation with native audio, multilingual dialogue with strong lipsync, multi-scene shots, and video continuation that carries framing and scene logic forward.”
https://x.com/fal/status/2084694140986777622
FLUX 3 Video, Part 1: Generation | Black Forest Labs
https://bfl.ai/blog/flux-3-video
introducing FLUX 3. beyond video, this is the first model to support interactions with the real world through a new action-prediction system. available now on Krea, more modalities coming soon.”
https://x.com/krea_ai/status/2084694677522157763
Two years later our first video model – FLUX 3 Video – is finally released🥹. This is such a strong, fun and versatile model made by the best team in the world @bfl_ai. We will add further variants and generation from references in the near future. I am also super excited about”
https://x.com/robrombach/status/2084695711141277919
What even is real anymore?”
https://x.com/bilawalsidhu/status/2085197812355010784
Qwen 3.8 Max and a new local 27B Qwen 3.8 is coming! Thanks @Alibaba_Qwen for featuring Hermes Agent in the release video!”
https://x.com/Teknium/status/2084140512777560537
I let OpenAI’s Codex app run ads for my business. It cut the video, published it, built the audience, set the budget then stopped at the Pay button and asked permission. The part that gets me: I watched the whole thing happen live inside the app.”
https://x.com/DevAdventur3s/status/2084054616946176324
1/ We’re entering the era of agentic commerce, and we believe that world models are the missing engine. Instead of browsing static product pages, agents will let you interact with products inside your own world before making decisions. Today, @DecartAI we’re releasing Anywear👇”
https://x.com/AbermanKfir/status/2084816814593478714
Holy, those insanae releases: MiniMax released a 33B video model that generates synchronized stereo audio and runs on one RTX 5090. H3 combines text, images, video and audio references for generation and editing, with clips up to 15 seconds. ComfyUI’s optimized stack is”
https://x.com/kimmonismus/status/2084229681012711598
VLM backbone or World Model? What’s the right kind of training data? Google DeepMind’s Kanishka Rao on how we might land on the recipe that solves robotics in the next 2-3 years.”
https://x.com/TheHumanoidHub/status/2083067365462528413
Must-read papers of the week ▪️ Wonder: Video World Model Done Better ▪️ DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation ▪️ Parallel Decoding Distillation for Fast Image and Video Generation ▪️ GPT-Red: Automated Red Teaming via”
https://x.com/TheTuringPost/status/2084450502503526618
This is really cool work building off our “Interpreting Physics in Video World Models” paper. People may not realize this yet, but unsupervised latent space simulators are a big deal.”
https://x.com/soniajoseph_/status/2084157222892806197
Useful world models need something different from just more video. New CG-World is a large computer-graphics-derived dataset and protocol that proposes a new approach to training data for world models. ▪️ Its idea is that pixels are observations generated by an underlying”
https://x.com/TheTuringPost/status/2083342704281583668
it’s the summer of World Models”
https://x.com/taiuti/status/2084286971774664922
VideoNeuMat: Neural Material Extraction from Generative Video Models” TL;DR: extracts reusable neural 3D materials from generative video models by turning Wan 2.1 into a virtual gonioreflectometer, then reconstructing materials from just 17 generated views.”
https://x.com/Almorgand/status/2085043522651017277
The biggest blocker to scaling mobile AR experiences was making the 3d content itself. Now you can quite literally make the content on the fly using real time video models.”
https://x.com/bilawalsidhu/status/2085020660464603184
Working on a turbo time LoRA for MiniMax H3. Still adjusting my algorithm to handle audio, so that is borked. And I need a better dataset that is not slow motion, generating that now. These samples are 4 steps, without and with the LoRA.”
https://x.com/ostrisai/status/2084648469877141998
one of the most beautiful things about OpenAI is that every employee really has a voice. i wanted to capture what it feels like to work here, what our mission means to me, and why you should join us. so i made this video with Codex, shared it with the team, and they felt it was”
https://x.com/jxnlco/status/2082855170296205719
MiniMax H3 open weights are out, with the nodes already in ComfyUI. One Blender blockout, run against Seedance 2.0 at a fraction of the cost per generation, leaving more room for experimentation and iteration. To try this workflow, link below 👇”
https://x.com/ComfyUI/status/2084387277254644162
Big news: MiniMax-H3 by @MiniMax_AI is now the #1 open model in Video Arena: across both Text-to-Video and Image-to-Video. This is +280pts over the next best open model, hunyuan-video-1.5, and a huge improvement from Hailuo-2.3 at #27 (1199 pts) and Hailuo-02-pro at #28 (1197″
https://x.com/arena/status/2084408459991421319
The MiniMax-H3 video generation model is a lot of fun – here’s what I got on my M5 Pro Mac for the prompt “a rainbow colored skunk leaps over a mossy log in a supermarket” (~115GB model download, took around 45 minutes to generate)”
https://x.com/simonw/status/2084719238569435469
China’s MiniMax H3 is the first open model to top an AI video ranking
https://the-decoder.com/chinas-minimax-h3-is-the-first-open-model-to-top-an-ai-video-ranking/
MiniMax H3 is now the SOTA open video generation model in both @arena and @ArtificialAnlys benchmarks.”
https://x.com/MiniMax_AI/status/2084410437618352386
Creator homies – give me an AI video vibe check. What’s the current SOTA?”
https://x.com/bilawalsidhu/status/2083191558698848367
Having so much fun with MinMax-H3. Cannot believe we now have this video quality 100% locally 🚀”
https://x.com/victormustar/status/2084322394479464781
Good news for anyone with too many tabs: ChatGPT is getting better around the web. 🧩 Chrome extension: In Side Chat, ask about a YouTube video, reference your open tabs, or highlight text on a page and ask away. 💻 Desktop app: Get URL suggestions as you type, revisit”
https://x.com/ChatGPT/status/2082970812584432115
To train physical AI, synthetic environments and polished, tripod-mounted footage aren’t enough. You need the actual mess of the real world. 🚀Releasing RekaDaily-10k: 10,312 hours of unscripted, first-person household footage as collected, recorded by paid collectors in real”
https://x.com/RekaAILabs/status/2085413707157471505
Leave a Reply