Skip to content
ModelListedExternal
Browse files

LTX 2.3 Sulphur2 Distilled Diffusers

An uncensored video generation model based on LTX 2.3 supporting both t2v and i2v natively, as well as all of the other ltx 2.3 formats.

KindOtherBase modelOzzyGT/LTX-2.3-Distilled-1.1VersionRevision e123a97Bgrade

Model source

Kind
Other
File size
102 MB–5.91 GB
Base model
OzzyGT/LTX-2.3-Distilled-1.1
Version
vRevision e123a97
Updated
Sep 27, 2026
Downloads
43
Source
Hugging Face

Source description

Sulphur 2 (Distilled) — LTX-2.3 Diffusers conversion

Diffusers-format conversion of SulphurAI/Sulphur-2-base.


Sulphur 2

An uncensored video generation model based on LTX 2.3 supporting both t2v and i2v natively, as well as all of the other ltx 2.3 formats.

Join our Discord

Support the next version of the project, even just a few dollars would go a long way: Kofi


Get Started: To get started with the model, I recommend downloading either of the dev versions, (fp8mixed or bf16) and downloading the distill lora provided. By the way, I'm aware the workflows contain sulphur_final right now, just use the lora or use the full models, don't use both at the same time.

This model contains a prompt enhancer. The easiest way to get started with the prompt enhancer is by using it on lmstudio. The way to accomplish this is by going to your model folder inside lmstudio, then opening it up in your file explorer. Create a folder named "Sulphur", then a folder inside that called "promptenhancer". Inside that folder, place the gguf file and the mmproj file. Once you've done that, you should be able to load the prompt enhancer in lmstudio. There is no system prompt for it, just send the text (and an image) you'd like to be enhanced.

*As a note, this readme will contain better setup instructions and how to train on top of the model soon.


Links

Credits

Funders

  • Anonymous funder #1 — Supported the original Sulphur
  • Anonymous funder #2 — Made Sulphur 2 possible; this model wouldn't exist without them

Thank you to everyone who contributed.

Sources

1 source
Hugging FacePrimaryVersion e123a97d0aaae386ca930484be7928524f501f11
huggingface.co/CalamitousFelicitousness/LTX-2.3-Sulphur2-Distilled-Diffusers/tree/e123a97d0aaae386ca930484be7928524f501f11

Verified Aug 30

Download files

Model artifacts

12 artifacts

audio_vae/diffusion_pytorch_model.safetensors

safetensors · 102 MB · SHA-256 45dcb1c3cffc…9d12 · Hugging Face

Download file

connectors/diffusion_pytorch_model.safetensors

safetensors · 5.91 GB · SHA-256 e2bf5ca48db1…4722 · Hugging Face

Download file

transformer/diffusion_pytorch_model-00001-of-00008.safetensors

safetensors · 4.95 GB · SHA-256 373caee6df43…3492 · Hugging Face

Download shard

transformer/diffusion_pytorch_model-00002-of-00008.safetensors

safetensors · 4.92 GB · SHA-256 481d3f24262a…45a1 · Hugging Face

Download shard

transformer/diffusion_pytorch_model-00003-of-00008.safetensors

safetensors · 5.00 GB · SHA-256 b6b5a87863e5…4fff · Hugging Face

Download shard

transformer/diffusion_pytorch_model-00004-of-00008.safetensors

safetensors · 4.98 GB · SHA-256 73ca92ac7cb7…7a50 · Hugging Face

Download shard

transformer/diffusion_pytorch_model-00005-of-00008.safetensors

safetensors · 4.99 GB · SHA-256 c7c89dc8251f…afff · Hugging Face

Download shard

transformer/diffusion_pytorch_model-00006-of-00008.safetensors

safetensors · 4.99 GB · SHA-256 bab9654a8f6d…d495 · Hugging Face

Download shard

transformer/diffusion_pytorch_model-00007-of-00008.safetensors

safetensors · 4.98 GB · SHA-256 1153b7b77124…a499 · Hugging Face

Download shard

transformer/diffusion_pytorch_model-00008-of-00008.safetensors

safetensors · 577 MB · SHA-256 4a134f86cc8c…dacb · Hugging Face

Download shard

vae/diffusion_pytorch_model.safetensors

safetensors · 1.35 GB · SHA-256 425f0dfa227d…55c5 · Hugging Face

Download file

vocoder/diffusion_pytorch_model.safetensors

safetensors · 246 MB · SHA-256 c99dde145a98…e23c · Hugging Face

Download file

Source excerpts

2 excerpts

--- library_name: diffusers pipeline_tag: text-to-video base_model: - SulphurAI/Sulphur-2-base - OzzyGT/LTX-2.3-Distilled-1.1 base_model_relation: finetune tags: - text-to-video - image-to-video - video-generation - ltx-video - ltx-2.3 - sulphur-2 - distilled - diffusers --- # Sulphur 2 (Distilled) — LTX-2.3 Diffusers conversion Diffusers-format conversion of **[SulphurAI/Sulphur-2-base](https://huggingface.co/SulphurAI/Sulphur-2-base)**. --- **Sulphur 2** An uncensored video generation model based on LTX 2.3 supporting both t2v and i2v natively, as well as all of the other ltx 2.3 formats. Join our **[Discord](https://discord.gg/GSXJhKZ9V)** Support the next version of the project, even just a few dollars would go a long way: **[Kofi](https://ko-fi.com/fusioncow)** --- **Get Started:** To get started with the model, I recommend downloading either of the dev versions, (fp8mixed or bf16) and downloading the distill lora provided. By the way, I'm aware the workflows contain sulphur_final right now, just use the lora or use the full models, don't use both at the same time. This model contains a **prompt enhancer**. The easiest way to get started with the prompt enhancer is by using it on lmstudio. The way to accomplish this is by going to your model folder inside lmstudio, then opening it up in your file explorer. Create a folder named "Sulphur", then a folder inside that called "promptenhancer". Inside that folder, place the gguf file and the mmproj file. Once you've done that, you should be able to load the prompt enhancer in lmstudio. There is no system prompt for it, just send the text (and an image) you'd like to be enhanced. *As a note, this readme will contain better setup instructions and how to train on top of the model soon. --- **Links** - **([CivitAI Base Model](https://civitai.red/models/2594061/sulphur-2-base))** - **([CivitAI Quant Model](https://civitai.red/models/2630742))** **Credits** - **([TenStrip](https://huggingface.co/TenStrip))** — Testing & model merging ([His i2v merge of sulphur 2, highly recommend for i2v](https://huggingface.co/TenStrip/LTX2.3-10Eros)) - **@s1lv3rc01n** — Testing & model merging/quantizing ([silveroxides](https://huggingface.co/silveroxides)) - **@mov7162** — Musubi Tuner guidance - And many others — if you'd like to be on the credits and were not listed, reach out to the upstream autho...

Source context: 43 downloads · 0 likes · Pipeline text-to-video · Library diffusers · Repo CalamitousFelicitousness/LTX-2.3-Sulphur2-Distilled-Diffusers