FLUX.2 Dev is an open-weight all-rounder for detailed text-to-image generation, prompt-led editing, and iterative reference work. MachGen supports up to three input images, five output sizes from 1024 x 768 through 2048 x 2048, and seed control; review the FLUX.2 Dev Non-Commercial License for your intended use.
FLUX.2 Dev is Black Forest Labs' 32B open-weight model for image generation and editing. The published model uses the FLUX.2 Dev Non-Commercial License, so review the license for your intended use.
MachGen exposes both text-to-image and image editing with up to three ordered input images, five fixed output sizes, and seed control.
This table reflects the model routes and controls currently exposed by MachGen.
| Mode | Required input | Available settings |
|---|---|---|
| Text to Image | Text prompt | Output sizes: 1024x768, 1024x1024, 1024x1808, 2048x2048, 2048x1536 Seed control |
| Image Editing | Text prompt and up to 3 source images | Output sizes: 1024x768, 1024x1024, 1024x1808, 2048x2048, 2048x1536 Seed control |
Describe subject, composition, lighting, lens, materials, and style to generate a new still.
Attach up to three ordered source images and describe what should change or combine.
Choose one of the five fixed size presets shown in the playground. Billing is based on output megapixels.
Set a seed when you need controlled comparisons between prompt or setting changes.
For model background, technical details, and architecture, see the official FLUX.2 documentation.
Try this model in the MachGen Playground.
Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.
See Pricing for currently published MachGen rates. When available, the Playground estimate reflects the selected task and output settings.
Deployment: MachGen Hosted. FLUX.2 Dev runs on MachGen-managed inference infrastructure rather than being forwarded to a provider API.
The Playground and API sections on this page list the inputs and output settings exposed for this model.