ltx23_prepare_conditioned_latents

Build conditioned initial latents and the conditioning mask

Description

i2v (cond_latents has one latent frame): the encoded frame is repeated across all latent frames and only latent frame 0 is marked conditioned. Continuation (k latent frames): the prefix tokens are replaced and marked. Unconditioned positions start as pure noise.

Usage

ltx23_prepare_conditioned_latents(cond_latents, latent_frames, latent_height,
                                  latent_width, noise, cond_noise_scale = 0)

Arguments

  • cond_latents: Normalized condition latents [1, 128, k, H’, W’] from ltx23_encode_video_frames.
  • noise: Tensor [1, 128, F’, H’, W’] of standard noise (caller provides so seeding stays in one place).
  • cond_noise_scale: Numeric. Optional partial noising of the conditioned tokens (diffusers noise_scale, default 0).
  • latent_frames,latent_height,latent_width: Integers. Full latent geometry of the generation.

Value

list(latents [1, S, 128] float32 packed, conditioning_mask [1, S] float32 packed).