Resolve 21.1 batch render with AI assistants vs Formats bulk runs
Resolve 21.1 lets AI assistants like Claude batch render. Sume Formats bulk runs queue 1 to 100 items at concurrency 1 to 16 over one API call.
Blackmagic says DaVinci Resolve 21.1 integrates with AI assistants such as Claude, Claude Code and ChatGPT Codex to analyze projects, organize media, adjust settings and batch render. That is automation of your own Resolve project on your own machine. Sume's equivalent for hosted work is Formats bulk runs: one POST /v1/formats/{handle}/{slug}/bulk-runs queues 1 to 100 items, with a concurrency of 1 to 16.
How a bulk run behaves
The create call returns 202 and a queue receipt, which you poll at GET /v1/format-run-queues/{id}. There is no queue-level webhook, so polling is how you know it finished. A queue status of completed does not mean every item succeeded: read each item. The first-party catalog includes formats such as sume-slideshow, sume-recreate and sume-restyle; the catalog page lists what is available to you.
| Question | Resolve 21.1 with an assistant | Sume Formats bulk run |
|---|---|---|
| Where work runs | Your Resolve install | Sume workers |
| Batch size | Not stated on the page | 1 to 100 items per queue |
| Parallelism | Your hardware | Concurrency 1 to 16 |
| Finish signal | In the app | Poll the queue receipt |
| Per-item success | Not stated on the page | Check each item; completed is not all succeeded |
Choosing
Use Resolve automation when the source is a project with grades and fixed settings. Use bulk runs when the inputs are a list of URLs or prompts and the output is a repeatable Format. They can be combined: render masters in Resolve, upload them, then run a Format over the set.
Honest limits
- Queue size is capped at 100; larger sets need several queues.
- No queue webhook exists, so build polling with a sensible interval.
- Blackmagic's press release names the assistants but gives no limits, so none are compared.
Sources
Related posts
More in Formats
- Failed Format run codes: retry, continue, fix input or wait
Eleven error.code values a failed Sume Format run can carry, grouped by response: continue with previous_run_id, retry with a new key, fix input, or wait.
- Run 100 Formats overnight for an agency: Sume bulk queue explained
One POST queues up to 100 Format runs with a concurrency window of 1 to 16. Why a completed queue is not all succeeded, and the poll loop to run overnight.
- SaaS AI video feature: spend cap per plan and per-customer keys
To embed Format runs in a SaaS plan, set generation_spend_cap_usd from the customer's tier and derive Idempotency-Key from customer, order and version.
- Season output schema: episode videos and final cut as SumeMediaFile
Bind an output_schema with SumeMediaFile fields so a Sume run returns typed episode videos. The URL gate, 10% duration check and parts-versus-cut rule.
Written by Sume