Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
speed optimisation
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 LTX 2.3 workflow turns an uploaded image into a video; you can provide a custom prompt or use its prompt director.
The workflow file includes audio decoding and audio/video latent-combining nodes, but its description does not specify an audio result.
It is set up for SeaArt ComfyUI; the creator says it needs modification to work elsewhere.
It requires gemma_3_12B_it_fp8_scaled.safetensors, LTX23_audio_vae_bf16.safetensors, LTX23_video_vae_bf16.safetensors, and one other text encoder file.
It also requires comfyui-kjnodes (version 1.2.9) and RES4LYF (pin 0dc91c00c4c3fb38e7874fcd7a2a327765e8882c).
The creator describes it as work in progress and experimental.
No download URLs are listed for the required model files, and no model-use license is stated.
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
VAE · 348 MB · SAFETENSORS · bf16 · full · Unknown
LTX23_video_vae_bf16.safetensors
File unverifiedVAE · Unknown · LTX23 Video VAE Bf16.safetensors
Node pack · Registry
RES4LYF
FoundNode pack · Registry
