Loading
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
This is HQ Int8 Row ConvRot of LTX 2.3 v1.1 Distilled / Turbo model.
Source du modèle
Description de la source
This is HQ Int8 Row ConvRot of LTX 2.3 v1.1 Distilled / Turbo model.
Made from official BF16 model with SECourses Musubi Trainer Quantization app
You can download and use Musubi Trainer app for both training and quantization from here : https://www.patreon.com/SECourses/posts/secourses-musubi-137551634
To be able to use this model with very best performance please use our Torch 2.13 CUDA 13 ComfyUI installer with ready presets : https://www.patreon.com/SECourses/posts/download-comfyui-installers-and-presets-105023709
Sources
1 sourceArtefacts du modèle
1 artefactltx23TurboDistilledV11_v10.safetensors
safetensors · INT8 · 27,2 GB · SHA-256 7f065a0f2aa5…8348 · Civitai
TéléchargerExtraits de sources
1 extraitSource context: 337 downloads · Type Checkpoint · Base model LTXV 2.3
I also recommend our SwarmUI installer with ready SwarmUI presets : https://www.patreon.com/posts/download-swarmui-installer-and-presets-114517862
With our HQ Int8 Row ConvRot quant conversation and app and preset, the model quality is able to surpass GGUF Q8
With our ComfyUI backend, Int8 Row ConvRot is able to generate faster than FP8 Scaled literally 100% faster on RTX 3000, 4000 and 5000 series GPUs
Model quantization is taking around 3-4 hours on RTX 5090 since we do training like quantization with prodigy optimizer
Check model screenshots to see and learn more
