---
license: other
license_name: ltx-2-community-license-agreement
license_link: https://huggingface.co/Lightricks/LTX-2/raw/main/LICENSE
base_model:
- Lightricks/LTX-2
pipeline_tag: image-text-to-video
tags:
- ltx2
- t2v
- i2v
---
These are experimental FP8 merges of the LTX2 diffusion model. "All in ones" do not seem to be in the cards, as LTX2 has lots of (large) moving parts, including 2 VAEs for video and audio. So, for the meantime, I'm just going to focus on the diffusion model. For all other models needed to run LTX2, please refer here: https://huggingface.co/Kijai/LTXV2_comfy

Workflows for LTX2 are also rather messy, unfortunately, so I don't have a clean one to provide at the moment. I'm monitoring the development of NSFW LORAs, which are slowly rolling in.

**8 steps recommended**.

**I2V and First to Last Frame Tip:** Use low strengths for LTXVAddGuide nodes, like 0.4-0.6. Higher values seem to be more likely to get ignored or cause cuts. With low strength values, LTXPreprocess nodes that add compression artifacts might be reduced to <33 to preserve more detail. Also prompting things like "Special instructions: continuous shot with no cuts or transitions" might help.

**----- SFW VERSION HISTORY -----**

**V1:** I feel like the default distilled "overcooks" a bit too much, so I made a merge with 0.875 distilled + 0.5 of the "detailer" LORA to hopefully improve details. **euler_a/beta recommended.**

**----- NSFW VERSION HISTORY ----**

**V2:** This includes SSX, BetterBreasts, Improved Female Nudity and Female Masturbation LORAs, along with 0.875 distilled + 0.5 "detailer" LORA. **euler_a/beta recommended**.

Please support LORA creators and special thanks to the authors of these!