Victor Aragon

This is a pretty serious-looking node for directing characters with vid from within ComfyUI. Using this and generating a vid ref for something like SeeDance 2 would be a pretty neat way to use it~ github.com/yedp123/ComfyU…

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

@ComfyUI Music?

Comment here to get DM notified for tomorrow’s drop

Can’t wait for tomorrow 😋

@higgsfield_ai How to access? I can't find it

We saved SHOTS for the Holiday Sale finale - 67% OFF 🔥 One image in - cinematic shots from every angle out. Fully consistent. UNLIMITED Kling 2.6 + 365 days of UNLIMITED Nano Banana Pro. Biggest deal of the year. Retweet & reply & like - FREE 249 credits

@MEnesKirca Meta

AI can create perfect Static Ads now. Introducing "Meta Ads Creator" — the world’s first. Drag&Drop Any product get META-ready ads in seconds Retweet & comment “META” I’ll DM the full guide.

Post a video YOU generated. Just a video. No description

@systemdesignone Playbook

System Design Playbook: Giveaway Alert!! • System design fundamentals. • Condensed notes to read before the system design interview. • Must know concepts from real-world software engineering case studies. (24 hours only!) To get it: 1. Like, Retweet & Follow @systemdesignone 2. Reply "Playbook" Then I'll DM you the details.

Veo3.1 + Suno

Hey... Just wanted to SOFT LAUNCH this here.... We're releasing something fun soon. 👀 Want a sneak peek? Drop your picture here and we’ll run it through our next coming feature 🧩 For a reply - get exclusive discount promocode in your DMs now

HuggingFace just dropped 9 free AI courses and they’re insanely good. LLMs, agents, vision, 3D, audio, gaming all hands-on. All open-source. All free. Here’s what’s inside ↓

@javilopen instagram.com/otracuentamasd…

Metal Skin Panic MADOX-01 (1987)

Turn any GitHub repository into a visual treat! Simply replace "hub" with "diagram" in a GitHub URL and instantly view the entire codebase as interactive diagrams for easier understanding. 100% open-source.

Ollama v0.8 is here! Now it can stream responses with tool calling! Example of Ollama doing web search:

I finally released my new video on YouTube about Diffusion Models / Score-Based Generative Models. youtube.com/watch?v=B4oHJp… Literally planned this for a year and put so much work in. I think this approach to diffusion models is so intuitive and highly recommend giving that a go! Video is 38min long, so you will need some time to watch that haha.

@AndresOjedaOk @michalhershko @IsraelinUruguay Un partido que mantiene su postura. Negar genocidios a lo largo de la historia y apoyar al bando genocida.

Acabo de hablar con @michalhershko, Embajadora de @IsraelinUruguay Le manifesté nuestro absoluto apoyo ante el cobarde ataque recibido hoy por Irán, que se suma a la escalada de violencia han generado en la región los grupos terroristas como Hamás y Hezbolá.

Code: github.com/lamm-mit/PDF2A… HF space: huggingface.co/spaces/lamm-mi… @Gradio @_akhaliq @huggingface

Tools to watch in Fall 2024: #Metatailor The app - now close to its 2.0 release - refits 3D clothing to match any bipedal character, and exports game-ready output in FBX format It can be used with #B3D, #Unity and #UE5 cgchannel.com/2024/08/tools-… #gamedev #VFX @MetaTailor_app

@fofrAI @cubiq What about running a Reactor Face swap for each frame?

@cubiq One more, again the likeness is lost but the motion is good

With the same inputs, here's an output using IPAdapters and @cubiq’s recent weight scheduling and batching nodes. The person has changed a lot from the original animation, but the animation is good.