Itx-2.3-22b-dev-Q8_0.gguf
返回

Itx-2.3-22b-dev-Q8_0.gguf
793 1 12

摄影

品牌及视觉设计

写实

Itx-2.3-22b-dev-Q8_0.gguf

Itx-2.3-22b-dev-Q8_0.gguf

This is a GGUF quantized version of LTX-2.3.
unsloth/LTX-2.3-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance.

  • Important layers are upcasted to higher precision.
  • Uses tooling from ComfyUI-GGUF by city96.

There are two sets of GGUF's published. One for the dev model and one for the distilled. The distilled model is optimized for few step generation, think 4-8 steps. dev on the other hand needs more steps at least 20, but you get better outputs. The distilled variant is useful as a drafting model or a refining model.

In fact the workflow published below, uses the distilled lora on top of the dev model to refine the intial output.

此模型源自站外搬运（搬运地址: https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main ），若原作者对于本次搬运的结果存在异议，可点
申诉
我们会在 24 小时内，按照原作者的要求，对本模型展开编辑、删除或是转移给原作者等相关处理。由衷欢迎原作者入驻本站，共建 AI绘图的学习交流社区。

赤兔儿

赤兔儿

摄影

品牌及视觉设计

写实

模型信息

未冻结
原创作者：
unsloth
模型类型：
GGUF
基础模型：
Lightricks/LTX-2
文件名称：
models/unet_gguf/ltx-2.3-22b-dev-Q8_0.gguf
MD5：
88959c5433b7af79248aea50cac13711

Itx-2.3-22b-dev-Q8_0.gguf

This is a GGUF quantized version of LTX-2.3.
unsloth/LTX-2.3-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance.

  • Important layers are upcasted to higher precision.
  • Uses tooling from ComfyUI-GGUF by city96.

There are two sets of GGUF's published. One for the dev model and one for the distilled. The distilled model is optimized for few step generation, think 4-8 steps. dev on the other hand needs more steps at least 20, but you get better outputs. The distilled variant is useful as a drafting model or a refining model.

In fact the workflow published below, uses the distilled lora on top of the dev model to refine the intial output.

此模型源自站外搬运（搬运地址: https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main ），若原作者对于本次搬运的结果存在异议，可点
申诉
我们会在 24 小时内，按照原作者的要求，对本模型展开编辑、删除或是转移给原作者等相关处理。由衷欢迎原作者入驻本站，共建 AI绘图的学习交流社区。