LTX 2.3 first-to-last frame transition
Generate a video transition guided by two uploaded images, with jointly generated audio. Upload both a start image and an end image, then replace the example prompt with your subject, scene, movement, camera motion and transformation. Describe desired sounds or dialogue in the same prompt. The result is one video containing generated audio; there is no audio upload input. Endpoint images guide generation rather than guaranteeing exact copies, and exact dialogue or synchronization is not guaranteed.
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- Checking published version…
- Updated
- Oct 26, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Start image
LoadImage
End image
LoadImage
Transition and audio
CLIPTextEncode
Output width
PrimitiveInt
Output height
PrimitiveInt
Duration
PrimitiveInt
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Frame rate
PrimitiveInt
Start image guidance
LTXVAddGuide
End image guidance
LTXVAddGuide
Transition LoRA
LoraLoaderModelOnly
Start image framing
ResizeImageMaskNode
End image framing
ResizeImageMaskNode
Randomization
RandomNoise
Prompt guidance
CFGGuider
Sampling
SamplerEulerAncestral
Video encoding
CreateVideo
Video file
SweetTeaPreviewVideo
Start image preprocessing
LTXVPreprocess
End image preprocessing
LTXVPreprocess
Noise schedule
ManualSigmas
What you need
- Model files
- 27.5 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Output
- Transition video with generated audio · video
Requirements
Models
3Text 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
- Not resolved
LoRA · Hugging Face · valiantcat/LTX-2.3-Transition-LORA
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source