ShortGPT vs Pixelle-Video vs Jasna

Side by side, as alternatives to HeyGen. Rows that differ are highlighted; the strongest value in a row is marked. Unknown means no source yet.

ShortGPTRayVentura/ShortGPT

Pixelle-VideoATH-MaaS/Pixelle-Video

JasnaKruk2/jasna

HeyGenpaid product

Cost and coverage

Price

$0 software; you run it

Free plan (up to 3 videos/month); paid plans: see pricing page source ↗

AI avatar (talking presenter) videos

Partly

Yes

Video translation and dubbing

Partly

Yes

Script or prompt to video

Partly

Yes

Jobs covered

1 of 3 jobs

3 of 3 jobs

All 3

Popularity and activity (from GitHub)

Stars

8,053

29,209Top

3,242

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

283Top

—

Latest release

v0.3.0 · 2025-02-10

v0.1.15 · 2026-01-27

v0.11.3 · 2026-10-20Top

—

Commits / 12 wk

399

—

People committing / 12 mo

—

Issues opened / closed, 30 days

0 / 0

1 / 1

83 / 72

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, Gradio web app in Docker on your machine (or Google Colab)

Yes, local web UI on localhost:8501

Yes, desktop app and CLI that run on your GPU

Hosted by the vendor

Code licenceDiffers

MIT

Apache-2.0

AGPL-3.0

—

Model weights licenceDiffers

No bundled weights; uses cloud LLM and TTS services

No single bundled model licence: users select Ollama, ComfyUI/RunningHub workflows or direct model APIs. Each selected weight or provider keeps its own licence and service terms; Apache-2.0 covers the application code

Mixed: Jasna RF-DETR detectors Apache-2.0, Lada models AGPL-3.0, LTX weights under the LTX-2.x Community Licence, supporter models proprietary

—

Commercial useDiffers

Yes, MIT code; OpenAI/Gemini, ElevenLabs and Pexels terms also apply

Apache-2.0 code; check the licence of each image/video model or API you use

Public application source is AGPL-3.0-only, with its obligations. Commercial rights for each model/supporter component must be checked separately.

—

Paid services needed?Differs

A cloud LLM API key is required (OpenAI or Google Gemini); no local model option. ElevenLabs optional, Edge TTS free

Not required with Ollama + local ComfyUI (needs a capable GPU); otherwise paid LLM, RunningHub or image/video APIs

None for the free BasicVSR++ model; supporter models (UNet 4x, SD 1.5, LTX) need a paid supporter licence code

Subscription

HardwareDiffers

Not documented

GPU optional; NVIDIA GPU with 6 GB+ VRAM recommended for local ComfyUI generation

NVIDIA GTX 16-series/RTX 20-series or newer (compute capability 7.5+), or AMD Radeon RX 7000/9000 (experimental); SSD advised; LTX needs NVIDIA RTX, 8 GB+ VRAM and 16 GB RAM

—

Operating systemsDiffers

Docker (any OS with Docker) or Google Colab; manual install documented for Debian 11 only

Windows (all-in-one package), macOS and Linux (from source)

Windows and Linux (NVIDIA, or AMD experimental); macOS not documented

—

Setup effortDiffers

Medium, build and run the Docker image with an .env of API keys

Easy on Windows (all-in-one package); uv + ffmpeg on macOS/Linux; local ComfyUI is extra work

Easy; download the release for your system and GPU, unpack and run

—

Stars over time

Switch to Growth % to compare projects of different sizes fairly.

ShortGPT
Pixelle-Video
Jasna

Focus a point, use arrow keys, or tap for its value.

Tracked daily since 15 Oct 2026. Dashed history: estimated from public records of when people starred the repo. Lines connect observations only; gaps contain no measured points.

Growth % starts at each project's first observed point in the shown range. Zero-star starts are unavailable.

Notes for a video or post

A plain summary with today's date and a link to the sources. Check each project page before you publish.

ShortGPT vs Pixelle-Video vs Jasna (as alternatives to HeyGen)
Figures from RepoQuarry, 21 Oct 2026. Sources: https://repoquarry.dev/compare?ids=shortgpt,pixelle-video,jasna&product=heygen

HeyGen: Free plan (up to 3 videos/month); paid plans: see pricing page
ShortGPT: free software; does 1 of 3 HeyGen jobs
Pixelle-Video: free software; does 1 of 3 HeyGen jobs
Jasna: free software; does 3 of 3 HeyGen jobs

- ShortGPT: 8,053 GitHub stars, 0 commits in 12 weeks, licence MIT
- Pixelle-Video: 29,209 GitHub stars, 0 commits in 12 weeks, licence Apache-2.0
- Jasna: 3,242 GitHub stars, 399 commits in 12 weeks, licence AGPL-3.0

Where they differ:
- Runs on my machine?: ShortGPT Yes, Gradio web app in Docker on your machine (or Google Colab); Pixelle-Video Yes, local web UI on localhost:8501; Jasna Yes, desktop app and CLI that run on your GPU
- Code licence: ShortGPT MIT; Pixelle-Video Apache-2.0; Jasna AGPL-3.0
- Model weights licence: ShortGPT No bundled weights; uses cloud LLM and TTS services; Pixelle-Video No single bundled model licence: users select Ollama, ComfyUI/RunningHub workflows or direct model APIs. Each selected weight or provider keeps its own licence and service terms; Apache-2.0 covers the application code; Jasna Mixed: Jasna RF-DETR detectors Apache-2.0, Lada models AGPL-3.0, LTX weights under the LTX-2.x Community Licence, supporter models proprietary
- Commercial use: ShortGPT Yes, MIT code; OpenAI/Gemini, ElevenLabs and Pexels terms also apply; Pixelle-Video Apache-2.0 code; check the licence of each image/video model or API you use; Jasna Public application source is AGPL-3.0-only, with its obligations. Commercial rights for each model/supporter component must be checked separately.
- Paid services needed?: ShortGPT A cloud LLM API key is required (OpenAI or Google Gemini); no local model option. ElevenLabs optional, Edge TTS free; Pixelle-Video Not required with Ollama + local ComfyUI (needs a capable GPU); otherwise paid LLM, RunningHub or image/video APIs; Jasna None for the free BasicVSR++ model; supporter models (UNet 4x, SD 1.5, LTX) need a paid supporter licence code
- Hardware: ShortGPT Not documented; Pixelle-Video GPU optional; NVIDIA GPU with 6 GB+ VRAM recommended for local ComfyUI generation; Jasna NVIDIA GTX 16-series/RTX 20-series or newer (compute capability 7.5+), or AMD Radeon RX 7000/9000 (experimental); SSD advised; LTX needs NVIDIA RTX, 8 GB+ VRAM and 16 GB RAM
- Operating systems: ShortGPT Docker (any OS with Docker) or Google Colab; manual install documented for Debian 11 only; Pixelle-Video Windows (all-in-one package), macOS and Linux (from source); Jasna Windows and Linux (NVIDIA, or AMD experimental); macOS not documented
- Setup effort: ShortGPT Medium, build and run the Docker image with an .env of API keys; Pixelle-Video Easy on Windows (all-in-one package); uv + ffmpeg on macOS/Linux; local ComfyUI is extra work; Jasna Easy; download the release for your system and GPU, unpack and run

Stars show popularity, not quality. Check each project page before publishing.

Want share images and a ready video description? Open a project's creator kit.

Numbers: GitHub, fetched nightly. Facts: read from each project's own documentation, with the source on its page. How we check. RayVentura/ShortGPT ↗ATH-MaaS/Pixelle-Video ↗Kruk2/jasna ↗

ShortGPT vs Pixelle-Video vs Jasna

Stars over time

Notes for a video or post

Cookie preferences

Report a problem