multimodal-input

#multimodal-input

@novita_labs: Novita now supports DeepSeek-V4.1-Flash on @huggingface. • 552B backbone parameters • Native image and text input • Up …

X AI KOLs Following ↗ · 2026-09-10 Cached

Novita announces support for the DeepSeek-V4.1-Flash AI model on Hugging Face, featuring 552B parameters, native image and text input, a 1M-token context window, and controllable reasoning effort.

0 favorites 0 likes

#multimodal-input

@figmaweave: Turn text, images, or video into fully explorable 3D worlds. Then move around, direct your scene, and call the shots. @…

X AI KOLs Following ↗ · 2026-08-24 Cached

Figma Weave integrates Marble from @theworldlabs to enable the creation and exploration of 3D worlds from text, images, or video inputs.

0 favorites 0 likes

multimodal-input

@novita_labs: Novita now supports DeepSeek-V4.1-Flash on @huggingface. • 552B backbone parameters • Native image and text input • Up …

@figmaweave: Turn text, images, or video into fully explorable 3D worlds. Then move around, direct your scene, and call the shots. @…

Submit Feedback