#ai-video
10 tutorials, projects and news items tagged ai-video.
Seedance 2.5 looks the best, but 10 seconds costs about $1, so a two-minute video easily runs over $14. To save money we switched to H3 on jqsp, and the same explainer with a host costs under $0.50.
Let Meta Muse find recent viral TikToks in your niche, sort them into patterns, and break down their scripts. Then swap in your own product and generate a remake, with video generation free for now. Includes the prompt for studying viral videos.
Intermediate tutorial: the open-source project muse2api reverse-engineers the Meta Muse website into a video-generation API, and MuseAPI-Video adds a local studio on top. Have an agent install it and change the default password, bind your own Muse account, split your short into shots with one consistent style and queue them, then line the clips up on an infinite canvas. Includes risk notes. Includes 3 copy-ready prompts.
By his own account, he made three to five ads in one to two days. In one TikTok run, a single ad reached a click-through rate of about 15% and a cost per click of about $0.06.
Beginner tutorial: Use the open-source Hypit to give Claude Code or Codex a video-making skill. Hand it a reference video, have it break down the opening hook, pacing, and subtitle structure first, then swap in your product, presenter, and language to regenerate. Get a price quote before spending money, and reuse assets to batch out several versions. Includes 4 copy-ready prompts.
Beginner tutorial: In Dreamina, build a base portrait from a close-up and a full-body photo, split a reference outfit into single-item white-background images, swap outfits one at a time from the same base, generate an empty room, and use Seedance to turn the swap into a short video. Ends with rules for keeping the face steady over many edits. Includes 5 copy-ready prompts.
Beginner tutorial: Use the free, open-source givemotion project to have Claude Code or Codex check your computer, set up the tools, and turn one paragraph of description into a promo video, animated data chart, or vertical short. Review an overview image before rendering to MP4, then change only the parts you name in plain language. One video can also be batch-exported into several versions. Includes 4 copy-ready prompts.
Beginner tutorial: Build a Space in Meta Muse with one prompt, using an open-source Chinese pose gallery as the source. Only two safe categories are included. Each pose gets a stick-figure sketch and prompts for Seedance, Kling, FLUX and Midjourney. Then check the list, generate, and set a weekly auto-refresh for new poses. Includes 3 copy-ready prompts.
Beginner tutorial: Have an agent set up the tools, pick one of 66 Lemo-Opuscar styles, write each request with a fixed template and sources, then give plain-language feedback on the finished video. The result is an mp4 with voiceover, music and subtitles. Includes 4 copy-ready prompts.
Intermediate tutorial: When AI-generated indoor video keeps getting the space wrong, first have AI draw a floor plan, block out a previz in Blender and walk the camera through it. Once you confirm the first and last frames, turn it into a realistic video with Meta Muse, then check it frame by frame against the floor plan. If it is off, fix the blockout and start over. Includes 3 prompts you can copy directly.
