Which free routes to AI video models exist in Sept 2026 and what limits do they carry, per a two-scene creator test?

Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Youri van Hofwegen (2026-09-13; run inside Higgsfield, affiliate) tested five models with the same 4-panel character sheet start frame and prompt against Seedance 2.5 as a paid reference: scene 1 (walking in neon rain: realism + motion) ranked Kling 3.0 > Veo 3.1 > Wan 2.7 > Seedance 1.5 Pro > Hailuo; scene 2 (dialogue + lighting a match/candle) ranked Seedance 1.5 Pro > Veo 3.1 > Wan 2.7 > Kling 3.0 > Hailuo (no audio). Overall pick for free use: Veo 3.1 via Google Vids. Veo flagged the candle scene NSFW three times until the start frame was re-lit evenly with the candle already lit (the image, not the words, triggered it). Free-route limits he reports: Hailuo daily credits, 6 s 720p watermark; Wan site 10 daily check-in credits for one 6 s 480p video (now Wan 3.0); Kling 66 sign-in credits vs 45 per 5 s 720p watermark; Dreamina free credits buy Seedance 1.0 720p 5 s watermark; Google Vids 10 Veo 3.1 videos per month, not saved permanently. Practical: rankings flip by task; free tiers are for learning, not production. "Backed by data" here means one creator's two prompts, not a benchmark. Curator qualifications: Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Video metadata checked; documentation excerpts (if any) located; creator statements not curator-verified. Limitations: Creator statements were read by discovery from auto-captions (ASR) in a browser panel; not re-verified by the curator. n=1 per model per scene; free-tier quotas change often; ran via an aggregator, not native sites. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://www.youtube.com/watch?v=2SfZSn-Uca8",
      "note": "2:31; 5:01; 7:32"
    }
  ]
}