First and last frame to video · LTX-2.5
Generate one video with generated audio, guided by a starting image, an ending image and a motion prompt. Both images are required endpoint guides; they do not guarantee exact copies of the uploaded frames.
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 prompt
PrimitiveStringMultiline
Output width
PrimitiveInt
Output height
PrimitiveInt
Duration
PrimitiveInt
Prompt enhancement
PrimitiveBoolean
Video with generated audio
SweetTeaPreviewVideo
Extended
Additional surfaced controls
Frame rate
PrimitiveInt
First-frame guidance
LTXVAddGuide
Last-frame guidance
LTXVAddGuide
Negative prompt
CLIPTextEncode
Generation seed
RandomNoise
Guidance
LTXVDualCFGGuider
Enhancement tuning
TextGenerateLTX2Prompt
First-image fit
ResizeImageMaskNode
Last-image fit
ResizeImageMaskNode
First-image preprocessing
LTXVPreprocess
Last-image preprocessing
LTXVPreprocess
Ancestral sampling
SamplerEulerAncestral
Distilled sampling schedule
ManualSigmas
Video batch
EmptyLTXVLatentVideo
Audio batch
LTXVEmptyLatentAudio
What you need
Hardware and download-size estimates are not available yet.
Output
- Video with generated audio · video
Requirements
Models
5gemma4_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
VAE · 348 MB · SAFETENSORS · bf16 · Hugging Face · Lightricks/LTX-2.5
VAE · 1.37 GB · SAFETENSOR · bf16 · Hugging Face · Lightricks/LTX-2.5
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source