AI Video Upscale

AI-powered video upscaling with Real-ESRGAN and Waifu2x. Use when user asks to enhance, upscale, improve video quality, make HD/4K. Supports anime and real f...

Security Scan

The skill's files and runtime instructions match its stated purpose (local video upscaling using Real-ESRGAN/Waifu2x); nothing requests unrelated secrets or surprising system access.

Purpose & Capability

Name/description, SKILL.md, INSTALL.md and the provided script all focus on local video upscaling. Declared required binaries (ffmpeg, bc, md5sum) and downloads of Real-ESRGAN/Waifu2x releases are consistent with the stated functionality.

Instruction Scope

Runtime instructions and the script operate on local files only: extract frames, call local upscaling binaries, re-encode, and cache results. The script does not read unrelated system files, network endpoints, or secret env vars. It does create a cache directory under ~/.openclaw by default.

Install Mechanism

There is no automated install spec in the skill bundle (instruction-only), but INSTALL.md instructs the user to curl GitHub release zip files and unzip them into ~/video-tools. Those are standard GitHub release URLs (traceable) but downloading and executing prebuilt binaries always carries the usual trust risk—user should verify release source/checksums before running.

Credentials

No credentials or sensitive env vars are requested. INSTALL.md suggests optional environment variables that only point to local tool locations and a cache path. The environment access is proportional to the task.

Persistence & Privilege

Skill does not request always:true, does not modify other skills, and is run on-demand. It writes cache under a user-local path and creates temporary working directories; this is within expected scope.

Assessment

This skill appears coherent with its purpose: it runs local upscaling tools (Real-ESRGAN / Waifu2x) via a wrapper script. Before installing or running: (1) verify the GitHub release URLs and checksums for the prebuilt binaries you download, (2) inspect and run the script in a controlled environment—it will extract many frames and can use lots of CPU/GPU, disk, and memory, (3) note the default cache path (~/.openclaw/cache/video-upscale) and the 5-minute max duration limit in the script (adjust if you expect longer inputs), and (4) ensure you trust the prebuilt binaries (they run as local executables). If you want additional assurance, build the upscalers from source or run them in an isolated container/VM.

AI Video Upscale Skill

AI-powered video upscaling with progress tracking and job isolation.

Quick Usage

After installation (see below), run:

~/video-tools/real-video-enhancer/upscale_video.sh "{{filepath}}" "{{output_path}}" "{{mode}}" "{{preset}}" "{{engine}}" "{{job_id}}"

Or if you added the tool paths to your PATH:

upscale_video.sh "{{filepath}}" "{{output_path}}" "{{mode}}" "{{preset}}" "{{engine}}" "{{job_id}}"

Parameters

Parameter	Default	Description
filepath	required	Input video path
mode	auto	anime or real (auto-detects)
preset	fast	fast (2x) or high (4x)
engine	auto	waifu2x or realesrgan
job_id	auto	tg_<chatid>_<messageid>

Mode Selection

• anime → Waifu2x (better for anime with text)
• real → Real-ESRGAN (better for photorealistic)

Preset Selection

Preset	Upscale	CRF	Speed
fast	2x	20	Quick
high	4x	16	Slower

Example Prompts

• "Upscale this"
• "Upscale this anime clip"
• "Make this 4K"
• "Enhance in high quality, keep me updated"

Output Format

JOB_ID: tg_123_456
PHASE: EXTRACTING_FRAMES
FRAMES_TOTAL: 780
PHASE: UPSCALING
PROGRESS: 78/780
...
STATUS: OK
UPSCALED_VIDEO: /path/to/output.mp4

Installation

See INSTALL.md for setup instructions.