From the model card
Fields below are copied from the tags and counters on the HuggingFace repository SulphurAI/Sulphur-2-base at our last fetch. They are set by the uploader, not verified by us; rows with no tag are omitted. How this page is made.
- Publisher (HF namespace)
- SulphurAI
- Pipeline tag
- text-to-video
- Library
- Diffusers
- Weight formats
- safetensors, GGUF
- Lineage
-
- base model Lightricks/LTX-2.3
- quantized from Lightricks/LTX-2.3
- Downloads (HF counter at last fetch)
- 366,022
- Likes (HF counter at last fetch)
- 1,993
- Model card
- https://huggingface.co/SulphurAI/Sulphur-2-base
Use cases
- Experimental local text-to-video generation on consumer GPUs
- Testing GGUF-format video diffusion pipelines
- Creative prototyping where quality tolerances are low
Pros
- GGUF format enables quantized inference with lower VRAM
- Diffusers-compatible checkpoint structure
- Apache-like ecosystem tooling applies
Cons
- No published architecture spec or training dataset disclosure
- Output quality unverified against established video benchmarks
- Community model with no formal maintenance commitment
- Limited model card documentation makes evaluation difficult
Tags
diffuserssafetensorsgguftext-to-videobase_model:Lightricks/LTX-2.3base_model:quantized:Lightricks/LTX-2.3endpoints_compatibleregion:usconversational