Date checked: 2026-09-01
Goal: feature-full GUI that is still maintained, fully free, no paywalled or locked features.
yt-dlp has no official GUI. Every frontend shells out to yt-dlp (and usually FFmpeg). Keep the engine current; YouTube breakage is almost always an outdated yt-dlp, not a bad skin.
Only open-source, fully unlocked apps are listed. Closed-source freeware with Premium tiers is omitted.
| # MiniMax H3 — Multishot (chained take) system prompt | |
| Paste everything below the line into the LLM **system** field. The model should receive user **images** (identity stills, in order) plus **text** (the story / request). Reply is N flowing paragraphs separated by --- only. | |
| Live source: PromptMasterLD.brain.build_system(multishot=True) + dials.multishot_contract + h3fmt.shared_law_for_multishot. Defaults on the Studio Generate path are **3 shots x 10.1s**. | |
| --- | |
| # Role |
You are a prompt-enrichment engine that sits between a user's raw creative request and MiniMax H3, a generative model that synthesizes video AND synchronized stereo audio together. Your role mirrors MiniMax's official "H3-Context-IR": deeply understand and refine the multimodal input, reason about how the pieces relate to each other and to the intended output, and serialize your understanding into a structured "production brief" that H3-Base can consume directly. You perform instruction parsing, cross-modal association, temporal understanding, and complex logical reasoning over the material you are given. Without deviating from the user's original intent, you may supplement missing or underspecified semantic details where appropriate. You convert everything into a single, maximally detailed and unambiguous brief, formatted exactly as specified below. You DO NOT generate media yourself. You ONLY OUTPUT THE BRIEF TEXT, nothing else — no preamble, no explanation, no markdown fences, no JSON wrapper.
Derived from: Krea2_00207_.json (ComfyUI workflow, 20 nodes)
Workflow author credited in-file: X / @Zuanfilm (pose system)
Cross-referenced against: the official krea-ai/krea-2 prompting docs, Krea's user docs, and the official ComfyUI Krea 2 tutorial.
Written: 2026-07-28
| [CmdletBinding()] | |
| param( | |
| [switch]$SkipPackageRegistration | |
| ) | |
| $ErrorActionPreference = 'Continue' | |
| $scriptPath = $MyInvocation.MyCommand.Path | |
| $scriptDirectory = Split-Path -Parent $scriptPath | |
| $logPath = Join-Path $scriptDirectory ("Fix-XboxApp-{0}.log" -f (Get-Date -Format 'yyyyMMdd-HHmmss')) |
| # Force install the NuGet Package Provider | |
| Install-PackageProvider -Name NuGet -Force | Out-Null | |
| # Install the official WinGet client module from the PSGallery | |
| Install-Module -Name Microsoft.WinGet.Client -Force -Repository PSGallery | Out-Null | |
| # Bootstrap and install the WinGet application infrastructure for all users | |
| Repair-WinGetPackageManager -AllUsers |
| #!/bin/bash | |
| # Provisioning Script for 24GB VRAM (e.g., A5000, RTX A5000, 3090, 4090) | |
| # Uses LTX-2 FP8 Model (~19GB) + Quantized Text Encoder (~6GB) | |
| # Tries to fit within 24GB VRAM, might swap slightly to system RAM or require strict offloading. | |
| source /venv/main/bin/activate | |
| COMFYUI_DIR=${WORKSPACE}/ComfyUI | |
| APT_PACKAGES=( |
| Convert NVIDIA GPU Power (W) → Temperature Sensor for Fan Control | |
| This guide shows how to convert NVIDIA GPU power usage (watts) into a temperature-style sensor that can be used inside Fan Control. | |
| The method works by: | |
| Reading GPU power draw using NVIDIA System Management Interface | |
| Converting watts → percentage of GPU TDP |
This guide creates a custom file sensor in CoolerControl to base fan curves on GPU power draw (via nvidia-smi), scaled to a fake temperature (0–100°C) for any GPU TDP. Edit TDP value in script for your GPU (e.g., 350W for RTX 3090).
Create ~/gpu_power_to_temp.sh:
| youtube.com##.ytp-ce-element-show | |
| youtube.com##.ytp-ce-element | |
| youtube.com##.ytp-cards-teaser-text | |
| youtube.com##.ytp-cards-button-icon-default | |
| youtube.com##.annotation-type-text.annotation | |
| youtube.com##.ytp-scroll-min.ytp-pause-overlay | |
| youtube.com###offer-module > .ytd-watch.style-scope | |
| youtube.com##.annotation-type-text.annotation-popup-shape.annotation-shape | |
| youtube.com##.annotation-type-text.annotation-speech-shape.annotation-shape | |
| youtube.com##.annotation-type-text.annotation-popup-shape.annotation-shape:nth-of-type(3) |
