skip to content
gigarouter gigarouter
models / text-to-video · coming soon

Sulphur 2 Base

SulphurAI/Sulphur-2-base

published May 2026 · updated Jun 2026

Sulphur 2 Base is a text-to-video and image-to-video generation model based on LTX 2.3, supporting uncensored output.

status
coming soon
API providers
0
downloads / mo
716.9K

specs

TaskText-to-Video, Image-to-Video
ArchitectureBased on LTX 2.3
Input FormatsText and Image
Prompt EnhancerIncluded

about this model

SulphurAI/Sulphur-2-base is a text-to-video and image-to-video generation model based on LTX 2.3 that supports uncensored output natively for both modalities, as well as all other LTX 2.3 formats.

Key Capabilities

  • Native text-to-video and image-to-video generation without content restrictions.
  • Includes a prompt enhancer (available as a separate GGUF model) to improve input prompts and reduce face drift, particularly for long prompts or director-style inputs.
  • Recommended image-to-video workflow uses the community merge TenStrip/LTX2.3-10Eros, which applies layer-scaled merges of different steps for refined motion. This merge is explicitly reliant on Sulphur-2-base and has accumulated 251,997 monthly downloads and 433 likes, indicating strong adoption.
  • Version 1.2 of the merge leverages tuned connector data to further reduce face drift and improve explicit motion handling.

Ecosystem

Four finetunes and six quantized variants of the recommended merge are available on Hugging Face, including a third-party GGUF repository, providing deployment flexibility.

Availability

The model does not specify an open-source license. Official inference hosting is not yet available from Hugging Face Inference Providers; gigarouter offers it as a managed, OpenAI-compatible API.

best for

FAQ

What is Sulphur 2 Base best for?

It is best for uncensored text-to-video and image-to-video generation, leveraging the LTX 2.3 architecture.

What license is Sulphur 2 Base released under?

The model card does not specify a license; users should verify before use.

What input formats does the model support?

It supports both text prompts and images for video generation.

How can I call Sulphur 2 Base via the gigarouter API?

Use the OpenAI-compatible endpoint with your gigarouter API key, passing the model name and input parameters.

Does the model include a prompt enhancer?

Yes, a prompt enhancer is included; usage details may depend on the API implementation.

not yet live

We're benchmarking and onboarding Sulphur 2 Base as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.