PixArt-Σ

Name: PixArt-Σ
Author: fal

image

Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Capabilities

Show unsupported (16)

No supported capabilities recorded.

Model IDfal-ai/pixart-sigma

Providerfal

Creatorfal

Family—

License—

Statusactive

Typeimage

Input modalitiestext, image

Output modalitiesimage

Open weight—

Parameters—

Architecture—

Max resolution—

Resolutions—

Aspect ratios—

Batch size—

Release date2024-08-01

Sourceofficial

imagesPOST

https://fal.run/images

GET/v1/models/fal/fal-ai/pixart-sigma