I knew this guy was up to no good. Also, Maestro v2.4 is out. You too can make ridiculous things like this locally for free!
Maestro v2.4:
• Fullscreen gallery: swipe navigation, favorites, tap-to-pause, remembered sound, smoother transitions and pinch-zoom. Social video style (TikTok/Reels)
• Before/after image comparison with a draggable divider.
• Mobile improvements: reliable video posters, better viewport positioning and collapsible landscape sidecar.
• Gallery input routing: send images, captured frames and videos into the active Studio or Director mode.
• Qwen Image 2.1: CivitAI LoRA filtering, additional LoRA compatibility and lower multi-reference memory use.
• Director Qwen support: enabled compatible Qwen models, including Image 2.1, available for image generation.
• Experimental H3 Singularity with its recommended four-step Turbo LoRA.
• Prompt enhancement improvements: source-action parsing, dialogue ownership, continuity checks, focused repairs and music-driven prompting.
• New enhancement settings: 0–5 repair attempts and optional generation despite fidelity warnings.
• Director fixes: cast-specific performance instructions, dialogue formatting and language handling.
• Reliability fixes: Face Refiner cleanup, Recast memory, API-key saving, remote LLM images and missing DramaBox guides.
AboutMaestroBlizaine/Maestro
I knew this guy was up to no good. Also, Maestro v2.4 is out. You too can make ridiculous things like this locally for free!
Maestro v2.4:
• Fullscreen gallery: swipe navigation, favorites, tap-to-pause, remembered sound, smoother transitions and pinch-zoom. Social video style (TikTok/Reels)
• Before/after image comparison with a draggable divider.
• Mobile improvements: reliable video posters, better viewport positioning and collapsible landscape sidecar.
• Gallery input routing: send images, captured frames and videos into the active Studio or Director mode.
• Qwen Image 2.1: CivitAI LoRA filtering, additional LoRA compatibility and lower multi-reference memory use.
• Director Qwen support: enabled compatible Qwen models, including Image 2.1, available for image generation.
• Experimental H3 Singularity with its recommended four-step Turbo LoRA.
• Prompt enhancement improvements: source-action parsing, dialogue ownership, continuity checks, focused repairs and music-driven prompting.
• New enhancement settings: 0–5 repair attempts and optional generation despite fidelity warnings.
• Director fixes: cast-specific performance instructions, dialogue formatting and language handling.
• Reliability fixes: Face Refiner cleanup, Recast memory, API-key saving, remote LLM images and missing DramaBox guides.