Export the Sora library before delete
Export at sora.chatgpt.com/sunset before OpenAI deletes Sora-associated data. Remaining ChatGPT/Sora credits go to Codex, not video.
7 min read
Flux 3 T2V is native audio to 20s
Flux 3 T2V is 34 credits for 5s, up to 136 at 20s, native audio. Black Forest Labs GA on 4 Aug 2026. One row, one job.
7 min read
Jev is a System One model, not an LLM
Jev is a System One model from TypeSafe AI, not an LLM. It returns a typed value and a calibrated probability from program state. It does not generate text.
5 min read
Jev: zero hallucinations means out of schema
Jev's zero hallucinations means zero out-of-schema outputs, not zero wrong answers. TypeSafe's own benchmark is ~68%, and the references are frontier models.
5 min read
LTX 2.3 Fast: from 20 credits, 4K, audio
LTX 2.3 Fast starts at 20 credits, native audio, up to 4K, 6–20s. Use it for cheap 4K sound takes. Skip it when SKU must hold or the hero is dialogue.
7 min read
Qwen-Image-2.1 generates a real alpha channel
Qwen-Image-2.1, released 20 September 2026, generates native RGBA with a true alpha channel up to 2K from a prompt, replacing generate-then-background-remove.
5 min read
Qwen-Image-2.1 runs on one consumer GPU
Qwen-Image-2.1 cuts the visual generator from 20B to 7B. BF16 weights are 14.2 GB, INT8 is 7.26 GB, and a Q8 run sits near 16 GiB, up to 17 GB at 50 steps.
6 min read
Seedance 2.0 Fast R2V is 55 credits
Seedance 2.0 Fast R2V is 55 credits (was 78), 720p, native audio, 4–15s. Full Seedance 2.0 starts at 44. Fast is the draft/ref row.
6 min read
Map Sora 2 durations to Versely rows
Sora 2 T2V is 4/8/12/16/20s. Map those lengths to Veo 4/6/8, Seedance 4–15 or 4–30, Flux 3 5–20, Grok Imagine 6–30.
8 min read
Sora 2 Pro storyboard after the API
The 10/15/25s Sora 2 Pro I2V storyboard row dies with the API. Replace by duration and stills: Seedance, Flux 3, Veo first-last, movie-mode.
7 min read
Sora API last-day checklist, 24 Sept
On 24 Sept 2026 the Sora API still answers until OpenAI pulls it. Export masters, stop new prompts, reroute remaining jobs.
8 min read
Ten references in one Qwen-Image-2.1 edit
Qwen-Image-2.1 composes up to 10 reference images into one scene by prefix KV cache reuse. Long prompts overload the encoder and add unsolicited Chinese text.
5 min read
Typed decisions for platform policy checks
An Instagram AI-label or unoriginal-Reel check is a fixed schema. Jev returns a typed value and a confidence score from text. It cannot see the video.
6 min read
Wan 2.7 edit is not a new generate
Wan 2.7 video edit is 20 credits of instruction edit, not a new T2V. Change the take you have instead of rerolling identity.
7 min read
Wan 2.7: pick T2V, I2V, or R2V
Wan 2.7 T2V and I2V are 16 credits; R2V is 20. Audio is null on these video rows. Need native audio? Use Wan 2.6 T2V, Seedance, or Veo.
7 min read
All-caps captions fail reading speed
All-caps is slower to parse and taller in the box. Hook posts abuse it. Ads and SDH should stay in sentence case so the mute pass can finish.
6 min read
ASR misses names and numbers
The pass that ships is a read of names, SKUs and prices. ASR is a draft. Burn after that pass. This is not a model page.
6 min read
Brand Kit and Approval Gates for Teams
What Versely brand kit stores vs standing rules and job briefs. When teams require human approve, budget ceilings, interrupt mid-run, who connects social.
9 min read
Brief UGC Ad Test Pack for Agent
How to brief Versely Agent for a UGC ad creative testing pack: offer and hook variants, Meta/TikTok, aspect, avatar rules, captions, budget, approval.
9 min read
Brief a Weekly Reels Pack for Agent
How to brief Versely Agent for a weekly Reels or Shorts pack: count, platforms, aspect, brand limits, sources, captions, budget, and approval.
8 min read
Burn-in captions for Reels and TikTok
Feeds do not enable a sidecar. Burn-in is the format for Reels, TikTok and Shorts. YouTube long-form can take an SRT.
6 min read
Caption reading speed is characters/sec
Reading speed is CPS, not a punchy preset. Two lines, then split. All-caps and emoji spend the budget. Check on mute; do not invent a house CPS.
7 min read
Captions on webinar clips after the cut
Clip the insight first, then caption the short. Multi-speaker Zoom mixes need speaker IDs. ASR on the full recording is not a finished track.
6 min read
Captions on UGC ads are the hook
The first three words on screen are the ad. Caption style is a creative test, not a post-process. Same transcript, variants you actually score.
6 min read