Cesar | SparkleSnap

Sharing HCI design and building local AI VTuber swarms and gamified language apps and renders. Let's connect.

[Cesar | SparkleSnap @cborgenkrans]

@anstapnever Stay calm and collected 😄😌 = win

[Cesar | SparkleSnap @cborgenkrans]

@TokenGremlin It was built with Sol and not Astra!? Woah 😍

[Cesar | SparkleSnap @cborgenkrans]

What would your AI VTuber sound like?
#aivtuber #animewaifu

https://t.co/iPWAp6FUkM

[Cesar | SparkleSnap @cborgenkrans]

Of course, I had to test the new GPT capacity for making gifs so, ladies and gentlemen, I created "a GIF of a funny bird who is flirting with a lion" #GPTImage !!

[Cesar | SparkleSnap @cborgenkrans]

@yituihi Absolutely gorgeous design! And a cute blob floating above her hand, I wonder who that is

[Cesar | SparkleSnap @cborgenkrans]

This week has been productive. Learning about sprite generation, pixel gifs, methods for using GPT Image 2.6 and also for using Grok Imagine, and Claude Code for infographics.

The current video game production benefits a lot from it all and I'm really excited to keep growing.

[Cesar | SparkleSnap @cborgenkrans]

Looping pixel attack of my PSO2 character, plus a sticker set with my character Kotoba-chan. GPT Image 2.6 and @Mayz1169's skill. One reference image to start. This is so cool!

[Kiki @Mayz1169]

GPT Image 2.6 - Skill Share 👾

Turn any character reference into looping pixel GIFs, from single moves to sticker sets and full movesets.

Tried it with my own character, and it works surprisingly well!

Free & open source. Links in thread 🧵

[Cesar | SparkleSnap @cborgenkrans]

@Mayz1169 Is that female Malfoy I spot! 😁

[Cesar | SparkleSnap @cborgenkrans]

@NigelWatsonTFTC Cool girls 😎🎶 We need the full movie

[Cesar | SparkleSnap @cborgenkrans]

@MiraMusic_AI 開始フレームから球体を操る動き、きれい。アニメーションもGPTでやれそう、というのがちょっとワクワクします。

[Cesar | SparkleSnap @cborgenkrans]

@zhu185178 I didn't know chatgpt can make videos!? I've used Grok Imagine. I'll have to try GPT Image 2.6!

[Cesar | SparkleSnap @cborgenkrans]

@thsottiaux I did notice that I could generate more than the usual limit ^w^

[Cesar | SparkleSnap @cborgenkrans]

@Xjohannesh @finnardley Thanks! It took a few tries: the first was a 62 s flat-vector film. I cut it in length then rebuilt it as a notebook with stickers. Have you tried making a video with it?

[Cesar | SparkleSnap @cborgenkrans]

I made a 25-second advice film with script, voice, characters and animation using Claude Code on Ultracode Max.

It started from an infographic prompt by @finnardley. I made it sticker-style.

The whole thing is a worker’s notebook. How I made it, so you can make your own.👇

[Finn @finnardley]

i just killed the infographics show with 1 claude opus prompt

they have 15M subs, a full team of writers, animators and voice actors behind every video

mine cost $0 and 20 minutes to make

im giving out the prompt for free, enjoy

<inputs>
Ask me for my topic (a what-if, a "why does X happen", a true story, or how something works), or pitch 3 with one shocking true angle each. Ask which image model I have (GPT Image 2, or another that takes reference images at 4K) and which voice service (ElevenLabs, or Kokoro for free). Then write a 55-65 s script and a shot plan, and show me both before you spend anything.
</inputs>

<direction>
A 1920x1080 flat vector explainer in the style of the big infographic animation channels. Every scene is a full illustrated place (a lab, a street, a classroom, a stage) with characters acting the line out.
Flat colour shapes, no outlines, one slightly darker flat shade for form, a muted palette (dusty blue-grey, slate teal, warm beige, navy, soft purple), salmon-pink skin, big heads, dot eyes.
A new scene every 2-4 s and a hard cut on every sentence that changes the idea. A white splat wipe (0.2 s in, 0.2 s out) between big sections. The camera always drifts 2-4% or pans.
Text lives only on things in the world: signs on posts, hanging boards, chalkboards, building panels and screens.
- It is typed in Montserrat 800 at 26-34 letters a second. Each letter arrives 1.45x big and 0.7 em to the right, then settles in 0.18 s.
- Ink is #2b2d42 on white boards.
- A red X (#d62828, 30 px round strokes, two strokes of 0.11 s each) goes over every wrong idea.
- Every date gets a white 330x120 card top left with an orange #f4a261 calendar.
- Headlines are white 92-96 px caps on a flat colour (#e2552f with drifting lighter puffs, or #5b3fa6 with slowly turning #6a4cb6 gears).
Banned: outlines, motion-design UI floating over the art (code editors, glass cards, checklists), emoji, burned-in subtitles, any channel's logo, a still frame longer than 1 s, and a character who doesn't move.
</direction>

<structure>
Length: the voice decides, 55-65 s at about 190 words per minute.
0 s a second-person hook that flips what the viewer assumes, acted out literally, then a red X on the denial line → 3-8 s the stakes in one shocking true line, with icons popping in one per word → 8-11 s the subject revealed under a spotlight, its name typed on a sign → 11-18 s the origin: the real place with its name typed on its own sign, a date card, people walking in or out of it → 18-24 s the types or parts, landing one by one on their names, each labelled → 24-25.5 s "so how does it work?" as a headline with question marks popping → 25.5-36 s the mechanism acted out in 2-3 places (a chalkboard, a machine, a map), with a counter rolling up to the big number → 36-46 s what it leads to, with characters who react (jump, turn, a "!" pops) → 46-55 s the twist that ties back to the hook → 55 s the last line is a question to the viewer, the viewer character from the hook reacts, and the sign holds to the end.
</structure>

<build>
1. Tools: Python, Playwright with Chromium, FFmpeg, faster-whisper, OpenCV, Pillow, librosa. Install what's missing and tell me what you installed.
2. Art: everything at 3840x2160, with 3-5 frames of the reference channel as style references (crop their logo off first).
- One EMPTY plate per scene: no people, straight-on, open floor, blank signs and screens to write on in code.
- Character sheets on solid chroma green #00B140, with nothing green on anyone.
- Draw any character who gestures a lot WITHOUT ARMS, only round shoulder sockets, so code draws the arms. Draw everyone else in the exact pose their scene needs: side view at a desk, side view walking, seen from behind, sitting.
3. Cutouts:
- The background is every pixel with G - max(R,B) over 40, within 110 of the median green, connected to the border.
- Add a 2 px soft alpha band, and clamp G to max(R,B) + 6 inside it.
- Split heads at the neck, drawing hands, and walkers' legs below the coat hem.
- Refill each hole with inpainting from the body's own colours (transparent pixels masked too), so a turning piece never shows a gap.
4. Voice:
- Pick it by measuring median pitch (pyin) and MFCC timbre against a clip of the narrator you want.
- Generate one take, cut pauses over 0.24 s to 0.16 s, and atempo it to the target length.
- Get word timestamps with faster-whisper. Every cut, sign and gesture starts on a real word.
5. Film: one HTML canvas where every frame is a pure function of time: window. seek(t), READY, END, and EV with the sound times. One function per shot.
- Arms: two-bone IK tubes (upper 118, lower 112, 36 thick for a 918 px tall sprite) with mitten hands that open, point or make a fist.
- Faces blink for 0.14 s every 2.7-4.2 s. Heads nod ±0.035 rad. Drawing hands scribble ±8 px.
- Walks:
- Thighs swing ±0.42 rad, and the knee bends 0.75·cos² on the swing.
- The hips drop so the planted foot stays down.
- The body moves 1.5 leg lengths per cycle, so feet never slide.
- Draw each plate inside the same camera transform as everything on it, and clamp the camera to the plate's edges.
- Things arrive with a spring, a squash or a white puff, never a fade.
6. Render: Playwright Chromium with --allow-file-access-from-files, 60 fps, 6 motion-blur subframes over half a frame, ffmpeg libx264 at CRF 16. Before rendering, show me two 16-frame contact sheets and fix empty boards, overflowing text, covered faces and black edges.
7. Sound:
- Music: a light curious documentary bed (free on Pixabay), 10-11 dB under the voice in every phrase.
- SFX: Mixkit, placed by their peaks. A typewriter tick on typed signs, a whoosh on wipes and drops, a pop on signs and icons, a hit on the red X, a ding on ticks.
- Mix to -14 LUFS.
</build>

<gotchas>
Some image models ignore "no arms"; GPT Image 2 follows it. On outline-free art a floating flood fill leaks into dark clothes, so key by border-connected green instead. Look up repeated words by their occurrence number (the third "and", the fourth "this"), or cuts land on the wrong line; scan the render for single-frame jumps and check that each one is a planned cut. When a scene has a screen or a sign, write on the plate's own blank one (measure its rectangle), never on a card floating over the art.
</gotchas>

<start>
Ask me for my topic, or pitch 3, then show me the script and the shot plan.
</start>

[Cesar | SparkleSnap @cborgenkrans]

@finnardley What I learned:
· Draft the whole film rough first, then polish
· Cut on word timestamps, so every change lands on a word
· Shorter is better. My first version was 62 s; this one is 25

[Cesar | SparkleSnap @cborgenkrans]

@finnardley The recipe:

One real situation, three things you can do on Monday
Hook → tension → the moment → a twist ending, around 25 s
Write for the voice: numbers as words, no colons
Draw the characters as sticker sheets
Animate in code, cutting on the words

[Cesar | SparkleSnap @cborgenkrans]

@finnardley The tools:
Voice: VoxCPM2, cloned zero-shot from a voice I designed, on my own AMD GPU
Characters: GPT image
Animation: HyperFrames (HTML → video, open source)
Claude Code ran the whole pipeline; I directed and reviewed every version

[Cesar | SparkleSnap @cborgenkrans]

I saw a really great X post about infomercials, but I lost track of it. I want to find it and learn more!

[Cesar | SparkleSnap @cborgenkrans]

@SumeruAI Hi Mugen (or do I call you Sumeru?) Loving your feed, interesting stuff!!
- appreciate your question! I asked my AI to answer, in this attached video.(she got a little full of herself at the end sorry lol). enjoy

[Cesar | SparkleSnap @cborgenkrans]

Just started a TikTok for an AI personality project.

Momotamu is an automated AI VTuber 1 year in the making — giving AI character and a virtual moving body.
Early experiments with voice, movement, and presence.

Join the first 24 hours:

https://t.co/J1CCX6Es0K #VTuber #AIArt

[Cesar | SparkleSnap @cborgenkrans]

@Stefan_3D_AI Oh, compatible with AMD GPU? I'll so try it out