Adobe Firefly Image 5 API: native 4 MP vs Sume resolution tiers
Firefly's Image5 model is described as native 4 MP with Instruct Edit. Sume does not list a Firefly model; it uses 512, 1K, 2K and 4K tiers.
Adobe's Firefly API overview describes the Image5 model as its latest, with native 4 MP resolution and a new Instruct Edit capability. Sume's image docs do not name a Firefly model, so you cannot call Image5 through Sume. What Sume offers is a normalized resolution tier of 512, 1K, 2K or 4K on the models that list it.
Adobe facts are from its overview page; Sume facts from the Image API docs, read 2026-10-01.
What does Adobe say Image5 does?
The page calls Image5 "a leap forward in realism, lighting, and composition" with native 4 MP resolution across photography, text and illustration. Instruct Edit lets you generate and refine in one workflow using natural language edits. It also points existing Firefly API users to a migration guide.
What are Sume's resolution tiers?
The docs define resolution as a "Normalized tier (512, 1K, 2K, 4K)" and say a model only accepts the values its catalog descriptors list. Read supported_parameters before pinning a tier. Slow configurations such as 4K, high quality and large n are the most likely to return a 202 job envelope.
| Topic | Adobe Firefly Image5 | Sume images |
|---|---|---|
| Resolution | Native 4 MP | Tier: 512, 1K, 2K or 4K, per model |
| Model choice | Firefly model versions | Catalog model id, or sume/auto |
| Endpoints | Not covered on the page | One sume endpoint per model in v1 |
Can I compare pixel counts directly?
Not from these pages. Adobe gives megapixels; Sume gives tiers, and the docs do not map each tier to a pixel count in the sections cited here. Check the catalog entry for the model you plan to use and measure the file you get back.
What happens if I send sume/auto?
Sume picks the family for you and never discloses which one ran. It is not listed in GET /v1/images/models, and job.model stays sume/auto. If you need a known family, pass a catalog id; see picking a model for product photos.
Sources
Related posts
More in Models
- Fish Audio Drama 3 single-word fix vs Sume sentence segments
Fish Audio says Drama 3 preview can fix a single word. Sume has no word-level repair: regenerate a sentence and join takes with Timeline audio concat.
- FLUX.2 flex steps and guidance: BFL has them, Sume does not
BFL lists adjustable steps and guidance only for FLUX.2 flex ($0.06/MP). Sume lists flux.2-flex but rejects unlisted parameters with 400.
- FLUX.2 max grounding search: what it is, what Sume lists
Only FLUX.2 [max] does web-grounded generation at BFL. Sume lists flux.2-pro and flux.2-flex, so grounding is not available there.
- Flux TTS expressivity -2 to 2 vs Sume's emotion guide
Deepgram's Flux TTS expressivity runs -2 to 2 (0 nominal). Sume TTS has no such dial: generation_config takes volume, speed and a free-text emotion guide.
Written by Sume