Adobe Firefly Image Model 5
Adobe's current Firefly image model, announced in public beta at Adobe MAX on 28 October 2025, generating at native 4 MP resolution without an upscale pass.
- Resolution
- native 4 MP without upscaling; Upscale API adds 2x / 4x / 6x
- Weights
- Not released
- API
- Yes
- Commercial use
- Permitted subject to conditions
It powers a conversational 'Prompt to Edit' tool and in-development layered, context-aware compositing. Reachable through the Firefly web app, Creative Cloud apps, and the Firefly Services API (v3 async generate endpoint), with an Upscale API offering 2x, 4x and 6x.
Adobe markets Firefly's own models as trained on licensed Adobe Stock and public-domain content and as commercially safe with IP indemnity on paid plans; we could not verify the indemnity terms from a fetched Adobe legal page.
- Depends on your plan tier. Adobe markets Firefly's own models as trained on licensed Adobe Stock and public-domain content and as commercially safe with IP indemnity on paid plans; we could not verify the indemnity terms from a fetched Adobe legal page
Specification
- What it takes in
- text, image
- What it makes
- image
- Maximum resolution
- native 4 MP without upscaling; Upscale API adds 2x / 4x / 6x
- Aspect ratios
- not established
- Controls
- editing-by-instruction, image-to-image, inpainting, outpainting, style-reference, reference-character-consistency
- Weights
- Not released
- API
- Yes
- Pricing
- not established
- Released or updated
- 2025-10-28
Supported aspect ratios and pricing are not established here. That means no page we could retrieve stated them, not that the model lacks them.
Strengths
- Native 4 MP output with no upscale step
- Lives inside Photoshop/Premiere workflows plus a services API
- Broad partner-model catalogue (FLUX, Google, Ideogram, Luma, OpenAI, Runway, Topaz, ElevenLabs) behind one interface
Weaknesses
- No per-generation pricing published in the API docs
- Model version IDs and supported sizes are not surfaced on fetchable docs pages
- Was in public beta as of the MAX 2025 announcement; GA status unverified
Best for
- Enterprise and agency pipelines that need documented content provenance and integration with Adobe tooling.
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- The Firefly API overview page names Image5 as 'Latest' with native 4 MP, but does not list model IDs or a version table; several candidate docs URLs returned 404. Whether a newer Image Model 6 exists could not be checked (web search budget exhausted).
- The partner-model list is as of the October 2025 announcement (Flux 1.1, Imagen 4, Gemini 2.5, Ideogram 3.0) and is certainly stale — firefly.adobe.com now advertises '30+ AI models'.
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
FLUX.1 Kontext [pro] / [max]
Instruction-driven image editing models from the FLUX.1 generation (2025), still exposed as live /flux-kontext-pro and /flux-kontext-max endpoints. Th
Image generation
FLUX.2 [dev]
32-billion-parameter open-weights checkpoint that does text-to-image plus single- and multi-reference editing in one model, released 25 November 2025
Image generation
FLUX.2 [flex]
Hosted FLUX.2 variant that exposes sampling steps and guidance scale as API parameters, letting callers trade quality and prompt adherence against spe
Image generation