ComfyUI Node
Empty LTX-2.5 AV Latent (Batch) ⚡
Joint video+audio latent in LTX-2.5 geometry: video [B,128,(len-1)//8+1,H/32,W/32] and audio [B,z,n_latents,bins] read from the audio VAE. Use this, not the MiniMax H3 empty-AV node, to drive an LTX-2.5 sampler.
Empty LTX-2.5 AV Latent (Batch) ⚡
- audio_vae
- LATENT
◄width768►
◄height512►
◄length97►
◄frame_rate24.00►
◄batch_size1►
Category🤖 CCTech/LTX-2.5
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| audio_vae | VAE | ltx-2.5-audio-vae-bf16.safetensors. Only its geometry is read here (latent channels, frequency bins, latents per second) — no encoding happens, so it costs nothing. | |
| width | INT | 76864–16384 | — |
| height | INT | 51264–16384 | — |
| length | INT | 971–16384 | Frame count. The video VAE compresses 8:1 in time with a causal first frame, so 8k+1 values (9, 97, 121...) tile exactly. |
| frame_rate | FLOAT | 24.001–120 | Sets the clip duration, which sets the audio latent length. Use the same value on LTXV Conditioning or the two streams drift apart. |
| batch_size | INT | 11–64 | Clips per job, each with its own noise from the sampler seed. The LTX-2.5 DiT is batch-aware, so unlike MiniMax H3 no patch node is needed — but VRAM scales with the batch. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| LATENT | LATENT | — |