@kaiganii
iAccount based inUnited States
About this account
- Account based in
- United States
- Connected via
- United States App Store
Account-level information from X, not a live location or the device used for a specific post.
Gen AI Video Creative Director & Founder, prev at Sony Pictures and Netflix. Co-host of 5ives podcast. CPP: Hailuo Minimax, OpenArt, Luma, Dreamina, Vidu
Los Angeles, CA
Joined April 2007
- Tweets0
- Following0
- Followers0
- Likes0
FULL VIDEO: I edited together close to 120 ChatGPT images into video clips made in
@Hailuo_AI
image-to-video to match the Dune trailer frame-by-frame in the style of Moebius
I've collected a lot of examples of animation styles for my research β so I thought, why not point AI at it and make a documentary.
youtu.be/gOKbF43zk0Y
I think Taruma is an underrated genius in the GenAI space, and you should study his "auteur script" closely. It's made a huge difference in the quality of my results.
SceneFlow Update: Introducing the Multi-Track Timeline & Studio Workspace.
SceneFlow isnβt an AI web app that generates video or scripts. Itβs an interactive player and alignment workstation where you bring your video and prompt together to verify what the model followed, what it missed, and adjust timing.
Over the past week, I rebuilt the two areas that caused the most friction: watching dense scenes without card clutter, and editing cue timings without fighting the player.
Here is whatβs new:
π Multi-Track Sync Timeline β Active cues now glide along dedicated horizontal tracks (Dialogue, Camera, Audio, Action, VFX, etc.). Overlapping events no longer fight for screen space or clutter the view.
π Filters & Zoom Presets β Mute or isolate specific categories in one click, and switch between 4s, 8s, and 16s zoom horizons to inspect rapid dialogue or step back for overall scene pacing.
π οΈ 3-Panel Edit Workstation β Rebuilt Edit Mode into a 3-column studio layout. Switching between Playback and Edit no longer resets your video to 0:00 or cuts audio.
π Live Loop Preview & Micro-Nudge Steppers β Adjust cue start/end times with Β±0.1s and Β±0.5s steppers while a continuous loop plays in real time. Tweak boundaries by ear until the cut lands right on the beat.
π€ Built-In Gemini Prompt & Schema β Need AI to help draft timestamps? Copy the official multimodal prompt and schema directly from the cues window, run it in Google AI Studio, and paste the JSON straight in.
π Studio Script Editor β A revamped 3-panel screenplay editor with an automatic section outline, word wrap that keeps line numbers strictly aligned, and a 1-click syntax guide.
π¬ Built for the "Auteur Script" β The layout and syntax are designed around my personal prompting framework (structuring scenes with intent, logic guardrails, and chained -> execution states). Hopefully, my next article will dive deep into this!
π Read the New Deep-Dive Article: taruma.substack.com/p/scenefβ¦
Links below π
πππ π€+π§ retweeted
SceneFlow Update: Introducing the Multi-Track Timeline & Studio Workspace.
SceneFlow isnβt an AI web app that generates video or scripts. Itβs an interactive player and alignment workstation where you bring your video and prompt together to verify what the model followed, what it missed, and adjust timing.
Over the past week, I rebuilt the two areas that caused the most friction: watching dense scenes without card clutter, and editing cue timings without fighting the player.
Here is whatβs new:
π Multi-Track Sync Timeline β Active cues now glide along dedicated horizontal tracks (Dialogue, Camera, Audio, Action, VFX, etc.). Overlapping events no longer fight for screen space or clutter the view.
π Filters & Zoom Presets β Mute or isolate specific categories in one click, and switch between 4s, 8s, and 16s zoom horizons to inspect rapid dialogue or step back for overall scene pacing.
π οΈ 3-Panel Edit Workstation β Rebuilt Edit Mode into a 3-column studio layout. Switching between Playback and Edit no longer resets your video to 0:00 or cuts audio.
π Live Loop Preview & Micro-Nudge Steppers β Adjust cue start/end times with Β±0.1s and Β±0.5s steppers while a continuous loop plays in real time. Tweak boundaries by ear until the cut lands right on the beat.
π€ Built-In Gemini Prompt & Schema β Need AI to help draft timestamps? Copy the official multimodal prompt and schema directly from the cues window, run it in Google AI Studio, and paste the JSON straight in.
π Studio Script Editor β A revamped 3-panel screenplay editor with an automatic section outline, word wrap that keeps line numbers strictly aligned, and a 1-click syntax guide.
π¬ Built for the "Auteur Script" β The layout and syntax are designed around my personal prompting framework (structuring scenes with intent, logic guardrails, and chained -> execution states). Hopefully, my next article will dive deep into this!
π Read the New Deep-Dive Article: taruma.substack.com/p/scenefβ¦
Links below π
Introducing SceneFlow: Script-to-Screen Synchronization for AI Cinema.
When we watch an AI-generated video, we usually only see the final result. The prompt that directed it remains locked away in a text file or prompt box.
You never get to see what the model actually followedβand more importantly, what it completely missed.
I built SceneFlow to change that. Itβs a free, open-source web tool that connects your written script or prompt with video playback side-by-side in real-time.
My goal isn't just to make a cool playback tool, but to make AI video more engaging and educational. By locking the prompt to the video timeline, you can study every single second:
β’ Did the model respect the camera dolly or did it invent its own move?
β’ Did the character action trigger on cue?
β’ Where did the prompt breakdown or fail, and what can we learn from those mistakes?
What SceneFlow does:
βΆ Synchronized Playback β Video player on the left, interactive script on the right, perfectly locked in real-time.
π¨ 8-Category Color Spectrum β Active lines light up across Dialogue, Action, Camera, Framing, Audio, VFX, Transitions, and Environment.
π¬ Dual Script Formats β Supports adapted Screenplays as well as state-machine "Auteur Scripts" with modular tags ([CAM], [ACT], [AUDIO]) chained with '->'.
π In-Browser Cue Editor β Highlight any text to create a cue, snap timestamps to the video with one click, and auto-align cues.
π 30+ Built-In Examples β Explore full synced scenes from The Written Motion anthology, character dramas, and kinetic action vignettes.
π Reading & Workspace Controls β 6 paper styles (including OLED Blackout & Slate for video overlays), adjustable column widths, and responsive video scaling.
β‘ 100% Client-Side & Private β Runs entirely in your browser with zero installation, no account needed, and full PWA support.
Whether you want to dissect my prompts (and my mistakes!), study how models interpret instructions, or sync your own projects:
π Try the Live App: sceneflow.taruma.my.id/ (Click +Guide for an interactive tour)
π» GitHub Repository: github.com/taruma/SceneFlow
π Official Launch Article: taruma.substack.com/p/scenefβ¦
βοΈ The origin of "Auteur Script": taruma.substack.com/p/from-cβ¦
Pick a scene from the catalogue, hit the spacebar, and see how prompts come alive on screen!
Here's the app: kaigani.github.io/skritch/
(Windows build coming)
You can just make things.
For years, the Skitch app has been a go-to utility for me to quickly capture, annotate and share imagesβ but it hasn't been well supported since it was acquired by Evernote.
(1/3)
There were always features I've wanted, like to be able to add and arrange multiple captures to the same image. I've also wanted a light video tool that would let me trim/edit/export frames. So -- I made Skritch.
(2/3)
Give AI your email... what's the worse that could happen?
AI: I've solved everyone's Inbox Zero problem!
I put Qwen Image 2.1 through its paces. It's not replacing Krea 2 or GPT Image 2.5, but it definitely has its place as an image edit model.
youtube.com/watch?v=JA-ThIY5β¦
Had a character reference sheet, popped it into @Hailuo_AI MiniMax H3 and got a 1980s style toy commercial, with a live action toy version.
πππ π€+π§ retweeted
Friends collect crypto.
Friends want to spend it.
$40,000 worth of prizes.
Vibeathon - build anything, make friends.