←
Ichel Park5,054 posts
Ichel Park avatar

Ichel Park

@ichelpark

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

◷ Joined September 2024▧ 33 Photos and videos
Ichel Park avatar
Ichel Park@ichelpark·Sep 22

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.

1:20
Ichel Park avatar
Ichel Park@ichelpark·Nov 13

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.

1:02
Min avatar
⟳ Ichel Park retweeted
Min@cloneismin·Nov 9

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

1:39
Ichel Park avatar
Ichel Park@ichelpark·Nov 8

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

Ichel Park avatar
Ichel Park@ichelpark·Nov 8

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

Ichel Park avatar
Ichel Park@ichelpark·Nov 8

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

0:09
Ichel Park avatar
Ichel Park@ichelpark·Nov 8

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.

Ichel Park avatar
Ichel Park@ichelpark·Nov 8

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

Ichel Park avatar
Ichel Park@ichelpark·Nov 8

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.

0:10
Ichel Park avatar
Ichel Park@ichelpark·Nov 7

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.

Ichel Park avatar
Ichel Park@ichelpark·Nov 7

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

Ichel Park avatar
Ichel Park@ichelpark·Nov 7

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.

0:10