
we never built a set. we never left the green screen. no location scout, no vfx team, no roundtrip to a comp artist. green screen in, finished shot out, right inside your timeline. this is shoty. let's make it real.

🎥 film director & k-pop music videos. building shoty, a cursor for video. a new world for video gen. la / seoul

we never built a set. we never left the green screen. no location scout, no vfx team, no roundtrip to a comp artist. green screen in, finished shot out, right inside your timeline. this is shoty. let's make it real.

Our YC application video. Hollywood’s best are already using Shoty. We’re DoubleZero. We’re building a beast of an AI video model—not another API wrapper. @garrytan @ycombinator, good luck saying no.

Today, we’re launching Clone. An agent harness that predicts your next prompt. - Clone Mode keeps prompting your AI agents and never stops till done - 93.9% prompt prediction accuracy, outperforming Astra and Opus - You can use your own ChatGPT or Claude subscription Want to push agent-maxxing to the limit? clone.is/you

the open-source video mask editor highlights suspicious flicker and supports borrowing a neighboring frame’s mask: github.com/knoic/comfyui-vid…

flag frames where the mask vanishes or suddenly shrinks. copy the previous or next frame’s mask, then paint only the missing edge.

in comfyui, inspect the segmentation masks on the timeline before sending them to wan, ltx, or h3.

one bad mask frame can wreck the whole video. find the dropout, borrow a neighbor mask, then rerun. steps below.

the open workflow includes video extension, motion transfer, and custom keyframes: github.com/seitanism/comfyui…

keep those inputs distinct, then test one change at a time. otherwise it’s hard to tell whether the motion, reference, or prompt caused a drift.

use a reference image for identity and design. use motion context for movement. use keyframes for the moments that must land.

stop asking one reference image to control everything. a comfyui h3 workflow separates motion context, multiple references, and keyframes. here’s a cleaner way to assign each job.


tile the frame and window the timeline so each model call handles a smaller region. the node author says not to use this setup for fully generated first-stage video; it is aimed at video-to-video and upscaling.

in comfyui, generate the base clip normally first. then run the h3 temporal window + spatial tiles node as a second-stage upscale.

h3’s new node is for video-to-video, not magic first-pass generation. use temporal windows and spatial tiles to upscale without asking one pass to hold the whole frame. steps below.

repo: github.com/d3voz/openjutsu