Generate and edit images and videos via LibTV's APIs.
npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill libtv-skill
Please help me install this Agent Skill. Skill: libtv-skill Source: https://github.com/augustscl/awesome-xiawang-skills/tree/main/libtv-skill Command: npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill libtv-skill
This Skill enables teams to generate and edit AI-based images and videos using LibTV's capabilities, reducing manual production time and enabling rapid creative iteration.
Describe your vision to LibTV and start the generation/editing workflow to produce images or videos.
High-intent search queries and answers about installing and using this skill.
To generate images and videos from text prompts, you provide a natural language instruction to initiate the creation workflow, which then polls for results and downloads the finished media outputs.
Applying style transfer across scenes is achieved by feeding existing media references and editing instructions into the workflow, which processes the visual adjustments and outputs the modified video.
Yes, you can create storyboards and short promotional videos from a single natural-language prompt by running an automated sequencing workflow that handles end-to-end content generation.
Yes, the generation workflow supports image-to-video creation alongside text-to-image and text-to-video, allowing you to use existing visuals as references for new media generation.
To edit AI-generated videos and replace elements, you input editing instructions and reference media into the workflow, which applies the visual adjustments and returns the updated output.
You can produce storyboards, TVC-style promos, music videos, product demos, and educational clips by describing your vision to trigger the automated generation and editing sequences.
Darsh20009Generate AI images, videos, and fetch stock photos from prompts.
elevenlabsGenerate music from text prompts via the ElevenLabs Music API.
SpaceZephyrCreate and query agent-im conversation sessions with progress polling and file uploads.
ROYCE-8425Generate images, videos, and audio from text or images via fal.ai MCP.
