FLUX.2
FLUX.2 is an image model by Black Forest Labs. Vini connects text-to-image generation for this family. FLUX.2 features described by its author may include editing, but that does not create a reference-image input on this Studio option.
| Setting | Value |
|---|---|
| Model ID | flux2 |
| Name | FLUX.2 dev |
| Availability | available |
| Default for new nodes | no |
Common declared limits
Section titled “Common declared limits”| Setting | Value |
|---|---|
| Capabilities | text to image |
Limits apply together. initial is the studio choice for a new node; default is the fallback for an existing node without that value. Declared language or input support does not guarantee a successful result.
Prompting playbook
Section titled “Prompting playbook”Lead with the main subject and its action, then specify the setting and look. Phrase desired visible properties positively. For lettering, quote the words; for a brand color, associate the color explicitly with the object.
Studio example
Section titled “Studio example”On an Image node (Картинка), choose FLUX.2. Supply the input image or Element when the selected operation requires a reference. Use this original example as a starting point:
A small yellow delivery van parked beneath a stone arch, viewed from the side. Sharp lettering “POST” on the door. Soft overcast light and crisp detail.
Review the prompt and expected format before running. Compare the output against the source, including hands, face, object count, lettering and crop. Use the resulting scene image as a video first frame only after approving it. For automation, follow the supported MCP workflow.
Known failure modes
Section titled “Known failure modes”It cannot take a character reference through this Vini connection. Choose a reference-capable image model when a specific existing face or object must be supplied. Negative prompting is not supported by the author; positive descriptions are more appropriate.
Evidence and limits
Section titled “Evidence and limits”No dedicated current Vini visual benchmark is claimed for this connection. The absence of reference input is a contract fact, while output typography and color fidelity remain untested here.
An available reference input is not a guarantee of identity preservation. See reference workflows and image style samples. Generation and editing are different tasks; keep their evidence separate.
Reviewed 14 October 2026 against Vini’s image registry and dated research. Official model-author documentation checked on that date. Recheck the guidance when the model version or connected operation changes.