LTX-2.3 first and last frame video
Generate a video with audio between two endpoint images, guided by a motion and audio prompt, using the fixed LTX-2.3 distilled model.
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- Checking published version…
- Updated
- Oct 25, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
First frame
LoadImage
Last frame
LoadImage
Motion and audio prompt
CLIPTextEncode
Output width
PrimitiveInt
Output height
PrimitiveInt
Duration
PrimitiveInt
Extended
Additional surfaced controls
Frame rate
PrimitiveInt
First frame guidance
LTXVAddGuide
Last frame guidance
LTXVAddGuide
First frame fitting
ResizeImageMaskNode
Last frame fitting
ResizeImageMaskNode
Negative prompt
CLIPTextEncode
Seed
RandomNoise
Guidance
CFGGuider
Sampling noise
SamplerEulerAncestral
Video bit depth
CreateVideo
First frame preprocessing
LTXVPreprocess
Last frame preprocessing
LTXVPreprocess
Sampling schedule
ManualSigmas
Video encoding
SweetTeaPreviewVideo
What you need
- Model files
- 27.5 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Output
- Video with generated audio · video
Requirements
Models
2Text encoder · 8.80 GB · SAFETENSORS · bf16 · Hugging Face · Comfy-Org/ltx-2
Text encoder · 27.5 GB · SAFETENSORS · fp8 · full · Hugging Face · Lightricks/LTX-2.3-fp8
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source