BrokenSource/DepthFlow
🌊 Images to 3D parallax videos observed · 2026-08-28
Health v2 · maintenance only
85/100
- Activity 99
- Release rhythm 67
- Longevity 83
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 1166
- days_rel: 8
- days_push: 8
- n_releases_24m: 1
Adoption not part of the score
1512 stars · 121 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
DepthFlow is a free, open-source Python application and library that converts still images into 3D parallax effect videos using monocular depth estimation models and an optimized ray-marching GLSL shader. It renders high-quality, seamless-loop videos at any resolution via FFmpeg, with both a CLI and a Python API.
Use cases
- turn photos into 3D parallax videos
- animate still images with depth effect
- generate looping parallax animations for social media
- estimate depth maps from single images
- create 2.5D motion from digital art
- batch render image-to-video animations locally
When to choose
- you want free, local, watermark-free image-to-video parallax rendering
- you need high-resolution (up to 8K) GPU-accelerated output with seamless loops
- you want programmatic control over camera and animation via a Python API
- you want to use SOTA depth estimation models like Depth Anything v2
When to avoid
- you need a polished GUI or web interface (the Gradio WebUI was removed in v1.0)
- you want commercial use of non-Small Depth Anything models (CC BY-NC license restrictions)
- you need batch processing built in (removed in v1.0; use scripts instead)
- you lack a GPU or FFmpeg for rendering and encoding
Facets
application · maturity active
image-processing video-processing computer-vision machine-learning graphics cli computer-vision image-processing graphics artificial-intelligence python cross-platform cli parallax-effect depth-estimation depth-map image-to-video ray-marching glsl-shader ffmpeg depth-anything monocular-depth video gpu
10 sources
- readme: https://github.com/BrokenSource/DepthFlow · fetched 2026-08-28 · 49520ec92c55
- homepage: https://depth.tremeschin.com/ · fetched 2026-08-29 · 9c265420ab9b
- site_page: https://depth.tremeschin.com/docs · fetched 2026-08-29 · 08189c8ed31b
- site_page: https://depth.tremeschin.com/docs/inputs · fetched 2026-08-29 · f600dcf11bf2
- site_page: https://depth.tremeschin.com/docs/estimators · fetched 2026-08-29 · f37da36ac33e
- site_page: https://depth.tremeschin.com/docs/camera · fetched 2026-08-29 · 526e41d2e120
- site_page: https://depth.tremeschin.com/docs/animation · fetched 2026-08-29 · ae057b389010
- site_page: https://depth.tremeschin.com/docs/exporting · fetched 2026-08-29 · 30260a64230f
- registry_pypi: https://pypi.org/pypi/depthflow/json · fetched 2026-08-29 · 377b030a2fa4
- site_page: https://depth.tremeschin.com/changelog · fetched 2026-08-29 · 789e9d1c5013
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| BrokenSource/DepthFlow | main | 85 |
For agents
markdown · JSON · MCP: product_card(name="BrokenSource/DepthFlow")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem