Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Animate a starting image into one video with generated audio using LTX-2.5. Upload a first frame and describe the scene, action, camera movement, and desired sounds or dialogue. There is no audio-upload input.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
Scene and audio prompt
PrimitiveStringMultiline
Output size
ResolutionSelector
Duration
PrimitiveInt
Frame rate
PrimitiveInt
Prompt enhancement
PrimitiveBoolean
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Generation mode
PrimitiveBoolean
Initial image guidance
LTXVImgToVideoInplace
Refinement image guidance
LTXVImgToVideoInplace
Generation variation
RandomNoise
Refinement variation
RandomNoise
Generation guidance
LTXVDualCFGGuider
Refinement guidance
LTXVDualCFGGuider
Generation sampling
KSamplerSelect
Refinement sampling
KSamplerSelect
Enhancement settings
TextGenerateLTX2Prompt
Video encoding
CreateVideo
Video output
SweetTeaPreviewVideo
Initial noise schedule
ManualSigmas
Refinement noise schedule
ManualSigmas
Image preprocessing
LTXVPreprocess
Hardware and download-size estimates are not available yet.
Requirements
gemma4_e2b_it_bf16.safetensors
File unverifiedText encoder · Hugging Face · Comfy-Org/gemma-4 · Gemma 4
gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors
File unverifiedText encoder · Hugging Face · Lightricks/LTX-2.5 · LTX 2.5
Checkpoint · Hugging Face · Lightricks/LTX-2.5 · LTX 2.5
ltx-2.5-audio-vae-bf16.safetensors
File unverifiedVAE · Hugging Face · Lightricks/LTX-2.5 · LTX 2.5
ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors
File unverifiedUpscaler · Hugging Face · Lightricks/LTX-2.5 · LTX 2.5
ltx-2.5-video-vae-bf16.safetensors
File unverifiedVAE · Hugging Face · Lightricks/LTX-2.5 · LTX 2.5
Node pack · GitHub · tea-time-labs/sweet-tea-nodes
