Text-to-Image

3 published entries across models, datasets and demos.

Models(1)Browse all

Text-to-Image

Flow-matching text-to-image model with region conditioning. The reference checkpoint for the PrismStream stack.

2.6B paramsDiffusersApache-2.019 Aug 202632k688

prismstream-demo

Text-to-Image

Text-to-image with region conditioning. Paint a mask, describe what belongs inside it, watch it argue with you.

A10GGradioApache-2.020 Aug 2026712

lora-trainer-lite

Text-to-Image

A one-screen front end over the MochiCore trainer, for people who want an adapter without reading a config schema.

ZeroGPUGradioMIT18 Jun 2026141