Glif

Glif shipped a skill that analyzes an uploaded video and generates titles, visualizations, and motion graphics in sync with the speaker. Try it for lectures and book promos if you want styled edits without manual compositing.

Fabian Stelzer showed a Glif agent that recreates reverse-poem ads and generates the copy, clips, voiceover, music, and final cut inside one workflow. Follow-up posts pointed users to a reusable prompt and another same-day Glif spot, making the format repeatable.

Creators shared repeatable Seedance 2.0 workflows for ComfyUI clip extension, GPT Image 2 shot planning, and fake-broadcast or iPhone footage. The examples push Seedance beyond isolated shorts into longer, more controllable production pipelines.

Creators are using Seedance 2.0 prompts to fake handheld UGC ads, paparazzi-style crowd scenes, and shaky-phone footage with blocked sightlines and flash spill. Similar realism demos in ImagineArt and Kling suggest this look is becoming a repeatable workflow.

Glif’s Creative Super Agent can now scan an uploaded clip and apply zoom effects automatically while still handling subtitles in the same workflow. Fabian Stelzer also showed the agent loading Seedance iPhone-style skills for POV horror footage, so users can try the new edit path on short clips.

Glif users showed a chat agent generating GPT Image 2 storyboards and passing them straight into Seedance 2 for anime shorts. The flow collapses storyboard prep and animation into one conversation, but still leans on seeded references and prompt setup.

Glif launched V2 as a chat-based creative agent that chains image, video, voice, and music models, and announced a $17.5 million seed led by a16z and USV. Early demos show multi-model ads and short films being produced inside single conversations instead of manual tool hopping.