Text to Image
Describe the scene, style, and text. Control ratio, size, and batch count from the same generator.
Einheitlicher Kreativ-Workspace
Swift-Image
Generieren, editieren und Referenzen mischen. UI-Marke Swift-Image, Phase-1-Adapter austauschbar.
Written by the Swift-Image TeamLast updated
BeispielergebnisLive-Generierung läuft über einen verfügbaren Provider-Adapter. Offizielle Swift-Image-Weights/API/Lizenz sind noch nicht öffentlich.
Showcase-Raster
Swift-Image showcase samples are original creative scenes for people, products, posters, spaces, multi-image synthesis, and edits.
Original sample scenes for people, products, posters, spaces, and multi-image synthesis.
One model direction, three tasks
Swift-Image is a single creative surface for three tasks: text-to-image, single-image edit, and multi-image reference.
A single creative surface for text-to-image, single-image edit, and multi-image reference.
Single Image Edit
Upload one image and rewrite lighting, wardrobe, background, or layout with prompt-led edits.
Multi-Image Reference
Attach multiple references to steer identity, product look, or composition without rebuilding the UI.
Model research
6B / 3B / Turbo as reported in research materials
Swift-Image research materials describe 6B, 3B, and Turbo variants; they are research notes, not downloadable official releases on this site.
These are paper positioning notes, not downloadable official releases on this site.
Swift-Image 6B
Reported research focus on higher-capacity unified generation and editing quality. Not yet publicly available here.
Swift-Image 3B
Reported mid-size research variant balancing quality and cost. Treat metrics as research results only.
Swift-Image Turbo
Reported faster research profile for interactive loops. Availability remains pending public release.
Source framing: reported / research result / not yet publicly available. This product does not claim official Swift-Image weights or partnership.
Key figures at a glance
Swift-Image product copy uses concrete, attributable numbers from the paper and this SaaS credit table.
- Reported parameters
- 6B / 3BPaper variants for Swift-Image and swiftimage research profiles
- Reported training budget
- ~243K GPU hoursCited from arXiv:2608.20334 for the 6B renderer
- Live creative modes
- 3 modesText-to-image, single-image edit, multi-image reference
- Workspace credits
- 10 / 16 / 24Credits per 1K / 2K / 4K swift image output on this site
Citations & quotations
Swift-Image research claims on this page cite the public preprint; live generation still uses a replaceable provider adapter for everyday swift image work.
"We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing."
"Swift-Image achieves leading aggregate performance among evaluated open-source models with only 6B parameters and 243K GPU training hours."
"For efficient deployment, structural pruning and few-step distillation produce 3B and accelerated variants."
Creative workflow
A Swift-Image job moves prompt → reference understanding → generation → result in four steps.
Prompt → reference understanding → generation → result.
- 01
Prompt
Start from text, templates, or a pasted brief.
- 02
Reference understanding
Optional single or multi-image uploads guide identity and style.
- 03
Generation
Submit through Nuxt server APIs with the active provider adapter.
- 04
Result
Review, retry, or continue in the dashboard workspace.
FAQ
Is this the official Swift-Image model service?
No. The UI brand is Swift-Image, but official weights, API, and license are not publicly available. Live tasks use a replaceable provider adapter.
What can I do in the hero generator?
Text-to-image, single-image edit, and multi-image reference with aspect ratio and batch controls, plus loading, success, failure, and empty states.
What do 6B / 3B / Turbo mean on this site?
They summarize research positioning from public materials. They are not downloadable model packages on this website.
Which provider runs generation today?
Phase 1 routes through the existing GPT Image 2 BFF under a Swift-Image display label. The adapter can be swapped server-side later.
Do I need an account?
Browsing is open. Generation, history, and billing use the shared za-center auth and credits flow.
Will pricing claim official model licensing?
No. Pricing describes the unified creative workspace and credits. It does not claim purchase of official Swift-Image model rights.
Open the Swift-Image workspace
Continue in the dashboard for history, settings, and the same model/mode/size state used on the homepage.