Research index

Research profiles

Every tool we track, grouped by what it actually does. Three carry published research; the rest are marked Not researched rather than filled in with estimates.

Text & image to video

  • Kling AI Moderately supported Complex physical movement and holding a character's face steady across a shot.
  • Higgsfield Not researched Camera-move control and stylised cinematic shots, with access to several models in one place.
  • Runway Gen-4.5 Limited evidence Creative and editorial work — generative editing, motion brush and in-context controls.
  • PixVerse Not researched Fast short-form output for TikTok, Reels and YouTube Shorts on a low monthly budget.
  • Luma Dream Machine Not researched Naturalistic motion and image-to-video from a single still.
  • Vidu Not researched Reference-to-video — feeding it a character or object and keeping it consistent.
  • Google Flow Not researched Scene-by-scene filmmaking with Veo, if you are already inside Google's AI subscription.
  • Sora 2 Not researched Prompt-faithful scenes with native audio, if you already pay for ChatGPT.

Avatars & presenters

  • HeyGen Not researched Marketing and social video with a talking avatar, plus voice cloning and translation.
  • Synthesia Not established Corporate training and explainer video — 130+ languages, built for teams rather than creators.

Upscaling & restoration

  • Topaz Video AI Not researched Upscaling, denoising and frame interpolation on footage you already have.

Editing & assembly

  • InVideo AI Not researched Turning a script or prompt into a finished edit with stock footage, subtitles and voiceover.
  • CapCut Not researched Free general-purpose editing with AI helpers, strongest for short-form social.