A simple workflow for using the spatial upscale stage in LTX 2.3 to upscale any video. The LTX2.3 model upscales videos but adds its minor details and variations to the video.V2.0<ul><li>Played around with sigmas for the upscale. Consistency to original video has been improved significantly.</li><li>No need to bypass individual nodes anymore. Use the Groups bypasser node to enable or disable the generate audio module</li><li>Works better with prompts describing the video or the audio you want</li><li>LoRA dependency is reduced, but will do better with them for specific scenarios</li></ul>V1.0<ul><li>LTX2.3 model adds realism to the video while upscaling with added details</li><li>The workflow can upscale to 1.5x or 2x, depending on the spatial model used (Download from LTX2.3 Huggingface repo)</li><li>One of these nodes needs to be bypassed depending on whether the original video has audio - LTXV Audio VAE Encode or LTXV Empty Latent Audio</li><li>A LoRA might be needed based on the content of the video</li><li>A brief description of video for positive prompt or can be left empty</li></ul>

LTX2.3 Upscaler (with added detail)

V2.0<ul><li>Played around with sigmas for the upscale. Consistency to original video has been improved significantly.</li><li>No need to bypass individual nodes anymore. Use the Groups bypasser node to enable or disable the generate audio module</li><li>Works better with prompts describing the video or the audio you want</li><li>LoRA dependency is reduced, but will do better with them for specific scenarios</li></ul>

Files with SHA256: d0ae306d22a6a9dc1405c03b34f172d05b71f53b93e136bc9f1c553b01576beb