Fonte do modelo
Trecho da fonte
Artefatos de modelo
24 artefatosdev/ltx-2-19b-dev-Q3_K_M.gguf
gguf · 9,28 GB · SHA-256 0a48fc4463ec…8cc3
dev/ltx-2-19b-dev-Q3_K_S.gguf
gguf · 8,65 GB · SHA-256 f0f4164873a9…483b
dev/ltx-2-19b-dev-Q4_0.gguf
gguf · 10,8 GB · SHA-256 d4de6c7cee24…ae1e
dev/ltx-2-19b-dev-Q4_1.gguf
gguf · 11,6 GB · SHA-256 38258cae8342…5679
dev/ltx-2-19b-dev-Q4_K_M.gguf
gguf · 11,9 GB · SHA-256 dd1e54cb4be0…99f0
Trechos de fonte
3 trechosdev/ltx-2-19b-dev-Q4_K_S.gguf
gguf · 11,0 GB · SHA-256 f2ffc5b8f897…ad22
dev/ltx-2-19b-dev-Q5_0.gguf
gguf · 12,7 GB · SHA-256 38eb061e0829…413d
dev/ltx-2-19b-dev-Q5_1.gguf
gguf · 13,5 GB · SHA-256 1846cb09d9e3…1889
dev/ltx-2-19b-dev-Q5_K_M.gguf
gguf · 13,5 GB · SHA-256 b1da8d0acaa7…3991
dev/ltx-2-19b-dev-Q5_K_S.gguf
gguf · 12,5 GB · SHA-256 36339c8a112d…078b
dev/ltx-2-19b-dev-Q6_K.gguf
gguf · 14,8 GB · SHA-256 15ce38acb11f…cabc
dev/ltx-2-19b-dev-Q8_0.gguf
gguf · 19,0 GB · SHA-256 6ecf273fa0ed…da36
distilled/ltx-2-19b-distilled-Q3_K_M.gguf
gguf · 9,28 GB · SHA-256 cb121295a670…b23a
distilled/ltx-2-19b-distilled-Q3_K_S.gguf
gguf · 8,65 GB · SHA-256 7a5e70f592a2…c26c
distilled/ltx-2-19b-distilled-Q4_0.gguf
gguf · 10,8 GB · SHA-256 f493c615582d…d71a
distilled/ltx-2-19b-distilled-Q4_1.gguf
gguf · 11,6 GB · SHA-256 978467836de8…b891
distilled/ltx-2-19b-distilled-Q4_K_M.gguf
gguf · 11,9 GB · SHA-256 dc18d3d83523…49f0
distilled/ltx-2-19b-distilled-Q4_K_S.gguf
gguf · 11,0 GB · SHA-256 319c413c2d98…e480
distilled/ltx-2-19b-distilled-Q5_0.gguf
gguf · 12,7 GB · SHA-256 ed631310e1b9…ba46
distilled/ltx-2-19b-distilled-Q5_1.gguf
gguf · 13,5 GB · SHA-256 3e7396cf18e1…b6b9
distilled/ltx-2-19b-distilled-Q5_K_M.gguf
gguf · 13,5 GB · SHA-256 8e2b53ea57cf…ac5c
distilled/ltx-2-19b-distilled-Q5_K_S.gguf
gguf · 12,5 GB · SHA-256 a41f15575b2b…94cf
distilled/ltx-2-19b-distilled-Q6_K.gguf
gguf · 14,8 GB · SHA-256 1908b61b0c61…8d7e
distilled/ltx-2-19b-distilled-Q8_0.gguf
gguf · 19,0 GB · SHA-256 199d4f098b52…8aa8
--- pipeline_tag: image-to-video tags: - image-to-video - text-to-video - video-to-video - image-text-to-video - audio-to-video - text-to-audio - video-to-audio - audio-to-audio - text-to-audio-video - image-to-audio-video - image-text-to-audio-video - ltx-2 - ltx-video - ltxv - lightricks pinned: true language: - en - de - es - fr - ja - ko - zh - it - pt license: other license_name: ltx-2-community-license-agreement license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE library_name: diffusers demo: https://app.ltx.studio/ltx-2-playground/i2v --- **Quantized GGUF version of Split LTX-2 checkpoint** **Original model Link:** [https://huggingface.co/Lightricks/LTX-2](https://huggingface.co/Lightricks/LTX-2) **Watch us at Youtube:** [@VantageWithAI](https://www.youtube.com/@vantagewithai) # LTX-2 Model Card This model card focuses on the LTX-2 model, codebase available [here](https://github.com/Lightricks/LTX-2). LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. [](https://www.youtube.com/watch?v=8fWAJXZJbRA) # Model Checkpoints | Name | Notes | |--------------------------------|----------------------------------------------------------------------------------------------------------------| | ltx-2-19b-dev | The full model, flexible and trainable in bf16 | | ltx-2-19b-dev-fp8 | The full model in fp8 quantization | | ltx-2-19b-dev-fp4 | The full model in nvfp4 quantization | | ltx-2-19b-distilled | The distilled version of the full model, 8 steps, CFG=1 | | ltx-2-19b-distilled-lora-384 | A LoRA version of the distilled model applicable to the full model | | ltx-2-spatial-upscaler-x2-1.0 | An x2 spatial upscaler for the ltx-2 latents, used in multi stage (multiscale) pipelines for higher resolution | | ltx-2-temporal-upscaler-x2-1.0 | An x2 temporal upscaler for the ltx-2 latents, used in multi stage (multiscale) pipelines for higher FPS | ## Model Details - **Developed by:** Lightricks - **Model type:** Diffusion-based audio-video foundation model - **Language(s):** English # Online demo LTX-2 is accessible right away via the following links: - [LTX-Studio...
Source context: 2900 downloads · 29 likes · Pipeline image-to-video · Library diffusers · Repo vantagewithai/LTX-2-GGUF
Source context: 3171 downloads · 28 likes · Pipeline image-to-video · Library diffusers · Repo vantagewithai/LTX-2-GGUF