10S nodes version with custom audio and prompt director
Runtime profile
Remaining hardware or download-size estimates are not available yet.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This workflow turns an image and a custom prompt—or a prompt director (LLM)—into an image-to-video result, with custom audio.
The workflow graph includes audio adjustment, audio trimming, and video-combination steps.
The creator says it is set up for SeaArt ComfyUI and needs modification to work elsewhere.
The listed model files are gemma_3_12B_it_fp8_scaled.safetensors, ltx-2.3_text_projection_bf16.safetensors, LTX2_audio_vae_bf16.safetensors, and LTX23_video_vae_bf16.safetensors.
The creator describes it as experimental and a work in progress.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 285 downloads · Type Workflows · Base model LTXV 2.3
Requirements
Text encoder · 12.3 GB · SAFETENSORS · Unknown
ltx-2.3_text_projection_bf16.safetensors
Not resolvedText encoder · Unknown
LTX2_audio_vae_bf16.safetensors
Not resolvedVAE · Unknown
LTX23_video_vae_bf16.safetensors
File unverifiedVAE · Unknown · LTX23 Video VAE Bf16.safetensors