Jordan Urbs

wow Seedance 2.5 is FUN had a blast making this pseudo AI ad using @AskVenice ...tutorial incoming! https://t.co/13mKYnQBWa

Aug 7

This repo has inspired the Venice Video Harness to now excel at editing your AI video generations. For @AskVenice power creators, the harness has been updated (link below) Let me know how it goes!

Apr 22

This is why the future is home devices for basic local intelligence, and @AskVenice to access everything else.

Jun 30

It's fascinating to experience AI models evolve. Here's a "should've used @AskVenice" short film I made using Veo 3.1 a couple months back, demonstrating just one of the infinite possible realities where privacy over your consumption of artificial intelligence is of the utmost importance. It's a neat little dystopic sci-fi world we dreamed up, Claude and I, which Nano Banana Pro and Veo 3.1 later brought to life inside a Claude Code harness using the Venice API. I even got to have fun in the

Mar 19

AI video is finally fun! and @AskVenice makes it as convenient as possible to explore your script, plan out your shots, craft your prompts, and compare your generations ... all in one interface!

Nov 6, 2025

Wan 2.5 for the first shot, Veo 3 Fast for the second shot Not terribly impressive aesthetics, but I find it pretty funny

Jan 3

I've been building this video production tool over the past week... using Claude Code to generate storyboards and Venice AI for the actual image generation. Started out pure vibe coding. Just talking to the AI, iterating on prompts, watching it scaffold the whole thing. (My favorite kind of afternoon honestly.) But then I hit character consistency issues across shots. Spent 3 hours debugging something that a proper spec would have caught in 20 minutes. Here's the framework I finally landed on

Dec 16, 2025

@AskVenice Tutorial: https://t.co/lsbXUQJ1aV

Aug 8

EDIT: I might actually keep my Gemini subscription to keep using Storybooks. It's pretty valuable as a parent

Oct 25, 2025

For average joes, Gemma 4 12b... @AskVenice for the step after that. I still wonder if getting a GPU (or more memory for your macbook etc) is really going to pan out to be worthwhile in the end. I mean really how far will 32, 64, 128gb of memory really get you? "Running GLM 5.2 locally requires ~239 GB of RAM or unified memory for the realistic 2-bit dynamic GGUF quantization (UD-IQ2_M), which is the minimum viable configuration for local inference." Important to ask oneself WHY you are atte

Jun 28