model-split-screen
/model-split-screen
Make the "same prompt, two models" comparison video that every model launch produces (Claude Fable 5.2 vs Opus 5.5, Seedance vs Kling, Eevee vs Cycles): run one prompt twice under the same rules, log the real time and cost of each run, then lay the two results side by side (1920×1080) or stacked (1080×1920), started on the same frame, each with its name and its time and cost under it, optionally blind ("A" and "B" until the last seconds, then the reveal) and with a winner frame. scripts/split.py does the layout with ffmpeg and Pillow, so it works with an ffmpeg built without drawtext. Use when
Assessment and security
- Files in this package
- 5
- Scripts
- 1
- HTML comments
- 0
- URLs in SKILL.md
- 3
No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 1 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: scripts/split.py
What it does and when to use it
Make the "same prompt, two models" comparison video that every model launch produces (Claude Fable 5.2 vs Opus 5.5, Seedance vs Kling, Eevee vs Cycles): run one prompt twice under the same rules, log the real time and cost of each run, then lay the two results side by side (1920×1080) or stacked (1080×1920), started on the same frame, each with its name and its time and cost under it, optionally blind ("A" and "B" until the last seconds, then the reveal) and with a winner frame. scripts/split.py does the layout with ffmpeg and Pillow, so it works with an ffmpeg built without drawtext. Use when
Triggers from the description
Original author description
Make the "same prompt, two models" comparison video that every model launch produces (Claude Fable 5.2 vs Opus 5.5, Seedance vs Kling, Eevee vs Cycles): run one prompt twice under the same rules, log the real time and cost of each run, then lay the two results side by side (1920×1080) or stacked (1080×1920), started on the same frame, each with its name and its time and cost under it, optionally blind ("A" and "B" until the last seconds, then the reveal) and with a winner frame. scripts/split.py does the layout with ffmpeg and Pillow, so it works with an ffmpeg built without drawtext. Use when
How it works
- 1. Ask first
- 2. Run both under the same rules
- 3. Lay them out
- 4. Check before posting
- 5. Post copy that has worked
- Files
SKILL.md preview
---
name: model-split-screen
description: >-
Make the "same prompt, two models" comparison video that every model launch produces (Claude Fable 5.2 vs
Opus 5.5, Seedance vs Kling, Eevee vs Cycles): run one prompt twice under the same rules, log the real time
and cost of each run, then lay the two results side by side (1920×1080) or stacked (1080×1920), started on
the same frame, each with its name and its time and cost under it, optionally blind ("A" and "B" until the
last seconds, then the reveal) and with a winner frame. scripts/split.py does the layout with ffmpeg and
Pillow, so it works with an ffmpeg built without drawtext. Use when someone asks for a model comparison
video, "Fable vs Opus", "same prompt two models", a side-by-side or split-screen comparison with cost and
time, a blind "guess which one" test, or A/B of two renders or two edits. Not for a split screen inside a
story edit (varg-video-edit-library), comparing many models in a grid of stills (gpt-image-2-6), or
making the clips themselves (blender-code-film, code-game-trailer, varg-ai).
license: MIT
metadata:
author: vargHQ
version: "1.0.0"
compatibility: >-
Python 3 with Pillow (`pip install pillow`), ffmpeg and ffprobe. A font: Inter Bold if installed, else Arial
Bold (macOS) or DejaVu Sans Bold (Linux), or pass --font. A 9 s 1920×1080 split renders in under 2 s on an
Apple Silicon Mac. The two clips come from anywhere; no key needed.
allowed-tools: Bash(python3:*) Bash(ffmpeg:*) Bash(ffprobe:*) Read Write Edit
---
# Same prompt, two models
Every model launch fills X with the same format: one prompt, two models, two results side by side, and
the bill under each. On Claude Fable 5.2's launch day (2026-11-09) it was the fifth biggest format, with 824k
views across 9 posts. Cost and minutes have become part of the caption:
- [@EnvolDev](https://x.com/EnvolDev/status/2119907318729245180), "Cathedral of Ice": Fable $81.10 in
1 h 57 min vs Opus $45.97 in 3 h 11 min (291k views).
- [@MrTacticalX](https://x.com/MrTacticalX/status/2119955647542542439), a glass pool at sunset and at night:
Fable 1 h 30 min, $57.87 vs Opus 68 min, $14.39 (172k views).
- [@kinderlayer](https://x.com/kinderlayer/status/2120112222227648957) ran it blind: "guess which one".
The comparison only means something when both runs had the same chance. Most of this skill is about the
runs, not the layout.
## 1. Ask first
1. **Which two**: two models (Fable 5.2 vs Opus 5.5), two video models (Seedance 2.5 vs Kling 4 on varg),
two settings (effort low vs high), or two renders of one scene (Eevee vs Cycles).
2. **Frame**: side by side 1920×1080 for X and YouTube, stacked 1080×1920 for Reels, TikTok and Shorts.
3. **Open or blind**: names on screen from the start, or "A" and "B" with the reveal in the last 2–3 s.
4. **Winner frame**: none, or an orange frame around the one the person (not the agent) picks.
## 2. Run both under the same rules
- **One prompt, word for word**, saved to `prompt.txt` before the first run. No follow-up messages to one run
that the other did not get. If a run needed a nudge, say so in its caption.
- **Same tools and skills** installed for both, same machine, same time limit, same output size and length.
- **Fresh session per run.** Neither run sees the other's output.
- **Log while it runs**, not from memory: start and end time, tokens and dollars from the usage report (Claude
Code `/cost`, the API's usage, varg's `get_job_cost`), number of turns or retries. Write `runs.json`:
```json
{"prompt": "…", "left": {"name": "Claude Fable 5.2", "minutes": 117, "usd": 81.10, "nudges": 0},
"right": {"name": "Claude Opus 5.5", "minutes": 191, "usd": 45.97, "nudges": 0}}
```
- **Same moment in both clips.** Trim each result to the same beat (the first frame where the scene is
readable); the script then starts both on frame 1. A shorter clip holds its last frame.
- Keep both full results. People ask for them in the replies.
## 3. Lay them out
```bash
python3 scripts/split.py \
--left fable.mp4 --left-name "Claude Fable 5.2" --left-stats "1 h 57 min · \$81.10" \
--right opus.mp4 --right-name "Claude Opus 5.5" --right-stats "3 h 11 min · \$45.97" \
--title "Same prompt, two models" --prompt "A cathedral of ice, a ship, a whale" -o split.mp4
# vertical, blind until the last 3 s, with a winner frame after the reveal
python3 scripts/split.py --layout stack --blind 3 --winner left … -o split-9x16.mp4
```
- The title band holds one short line and the prompt in quotes, shortened to fit (the full prompt goes in the
post text or the first reply).
- Stats are the measured numbers from `runs.json`, in the same units on both sides.
- `--music bed.mp3` adds a bed cut to the film, faded out over the last second, at -14 LUFS. Keep it
quiet or leave it out: people watch comparisons muted and pause on frames.
- `--duration 12` cuts both to 12 s; default is the longer clip.
## 4. Check before posting
- Pause on 3 frames: names under the right clips (swapped labels are the classic mistake), stats readable on a
phone, nothing important cut by the panel crop.
- In blind mode, scrub to the reveal: the names must appear exactly when the "A"/"B" labels go.
- The caption repeats the numbers and says what was the same (prompt, tools, time limit) and what was not.
- No logos or brand marks in the title band unless they are the products being compared.
## 5. Post copy that has worked
- Lead with the surprise in numbers: "Fable took 1 h 57 min and $81; Opus took 3 h 11 min and $46. Same
prompt."
- Put the full prompt in the first reply, and both full-length results in the second.
- For blind posts, ask one question ("which one is Fable?") and reveal in a reply after a few hours.
## Files
- `scripts/split.py`: the layout (side or stack, open or blind, winner frame, music bed). `--help` for flags.
- `examples/eevee-vs-cycles/`: this skill's own test, the same Blender scene (blender-code-film) rendered by
Eevee and by Cycles, with measured seconds per frame.
Related: `blender-code-film`, `code-game-trailer`, `short-form-ffmpeg-cookbook` (crops and exports),
`varg-ai` (Seedance vs Kling on one key).
Files in this package (5)
- README.md 6 KB
- SKILL.md 6 KB
- examples/eevee-vs-cycles/README.md 1 KB
- examples/eevee-vs-cycles/runs.json 1 KB
- scripts/split.py 8 KB
Versions
The database has no other skills named model-split-screen.
Database snapshot: 13.11.2026 · package version fa2918bd6ec9 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100video-model-benchmark
Run one prompt through two or three AI video models and merge the 9:16 clips into one side-by-side video for X, labelled with model names and the shared prompt. Triggers on "compare video models", "side by side video", "video model benchmark", "veo vs seedance", "which video… - 100frame-capture
Records any web page (three.js, WebGL, canvas, GSAP, CSS animation, scroll-driven video) to a perfectly smooth 60 fps MP4 by running the page on a virtual clock, one exact frame at a time, and puts two recordings against each other as a labelled stacked or side-by-side… - 100ffmpeg-vapoursynth
VapourSynth integration with ffmpeg: vapoursynth demuxer reads VapourSynth script (.vpy) output as a video source for ffmpeg, enabling Python-based frame-server filtering with plugins like QTGMC (deinterlace), KNLMeansCL (denoise), dfttest, BM3DCUDA, MVTools, SVPflow, AviSynth+… - 100model-showdown
Give the same motion brief to three AI models, keep each first try, render all three the same way and stack them into one comparison video with model names and logos. Makes a 16:9 side-by-side for a newsletter and a 1080 x 1920 stacked reel for Instagram and TikTok. Use when… - 90seedance-video
Generate AI videos using ByteDance Seedance. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame, reference images), or (3) query/manage video generation tasks. Supports Seedance 1.5 Pro (with audio),… - 100seedance-video
Plan, write and render Seedance 2.5 and Seedance 2.0 videos. Use when the user wants a Seedance prompt, a multi-shot story, ad or explainer made with Seedance, or wants the video itself rendered. Writes prompts that follow the BytePlus Seedance prompt guide and plans shots; when…