This checkpoint was converted from a mixed ๐๐
๐๐ / ๐
๐๐ checkpoint by converting all ๐๐
๐๐ tensors to ๐
๐๐_๐๐๐๐
The main difference is ๐๐ก๐๐๐ค๐ฉ๐จ๐ข๐ง๐ญ ๐ฌ๐ข๐ณ๐ ๐๐ง๐ ๐ข๐ง๐๐๐ซ๐๐ง๐๐ ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ โ this is ๐ง๐จ๐ญ ๐ ๐ง๐๐ฐ ๐ฏ๐ข๐ฌ๐ฎ๐๐ฅ ๐ฌ๐ญ๐ฒ๐ฅ๐ or a visually enhanced model.
๐๐๐ฒ ๐๐จ๐ข๐ง๐ญ๐ฌ
โข Smaller checkpoint: about ๐๐.๐ ๐๐
โข Aggressive ๐
๐๐-๐๐๐๐ conversion
โข ๐๐ซ๐ข๐ ๐ข๐ง๐๐ฅ ๐ฆ๐จ๐๐๐ฅ ๐๐ซ๐๐ก๐ข๐ญ๐๐๐ญ๐ฎ๐ซ๐ ๐ฉ๐ซ๐๐ฌ๐๐ซ๐ฏ๐๐
โข ๐๐จ๐ฐ๐๐ซ ๐๐๐๐ ๐ฎ๐ฌ๐๐ ๐ than heavier BF16 checkpoints
โข Best for local ComfyUI users who want a smaller LTX-2.3 checkpoint
๐๐จ๐ง๐ฏ๐๐ซ๐ฌ๐ข๐จ๐ง
โข ๐๐
๐๐ tensors โ ๐
๐๐_๐๐๐๐
โข Existing ๐
๐๐_๐๐๐๐ tensors preserved
โข ๐
๐๐ and ๐๐ tensors preserved
For more details, files, and the full models repository:
https://huggingface.co/SOLRICKS/ltx23_srx_fp8_e4m3_experimental
Description
Experimental FP8_E4M3 repack.
Converted from a mixed BF16 / FP8 LTX-2.3 checkpoint by converting all BF16 tensors to FP8_E4M3.
This is an experimental dtype conversion / repack, not a newly trained model and not a merge.
FAQ
Comments (6)
hi, i'll go try it out.
do you need help with testing specific use cases?
We tried image-to-video and text-to-video conversions with no audio or video issues found. We are continuing to test and will next upload new images to try with the Civitai generator. Thank you.
could you please give a brief explanation of what is supposed to be different about this? or where it 'shines' compared to the base model? just a bullet-point description would be nice.
Just less vram usage. What I want to know is if its 1.0 or 1.1 as 1.1 is superior in every way.
The main difference is size/efficiency, not a new visual style: it is a smaller experimental FP8-E4M3 LTX-2.3 checkpoint, around 21.5GB, with tensor names/shapes preserved, tested in ComfyUI, and confirmed working with audio output; it is mainly intended for local ComfyUI users who want a lighter experimental inference checkpoint, not something designed to visually outperform the base model.
@ylvlylvuyv374212ย This is based on the current LTX-2.3 dev 22B / model_version 2.3.0 family, repacked to FP8-E4M3 for smaller checkpoint size and lower VRAM usage. No fine-tune or merge was done. Note: VRAM usage should be lower, but depending on the loader/workflow, system RAM usage may still be high or even slightly higher during loading/offloading.