LTX 2.3 I2V (image-to-video) Distilled LoRA
Animate ANYTHING with this LTX 2.3 workflow.
audio
i2v
ltx-2.3
simplesmenteia
video
0
37
Nodes & Models
Note
KSamplerSelect
PrimitiveInt
RandomNoise
LatentUpscaleModelLoader
ltx-2.3-spatial-upscaler-x1.5-1.0.safetensors
PrimitiveStringMultiline
PrimitiveBoolean
PrimitiveFloat
ManualSigmas
LoadImage
CheckpointLoaderSimple
ltx-2.3/ltx-2.3-22b-dev.safetensors
LTXAVTextEncoderLoader
gemma_3_12B_it_fp4_mixed.safetensors
ltx-2.3/ltx-2.3-22b-dev.safetensors
LTXVAudioVAELoader
ltx-2.3/ltx-2.3-22b-dev.safetensors
Reroute
LoraLoaderModelOnly
ltx-2.3-22b-distilled-lora-384.safetensors
ComfyMathExpression
CLIPTextEncode
LTXVPreprocess
ConditioningZeroOut
GetImageSize
LTXVConditioning
LTXVEmptyLatentAudio
EmptyLTXVLatentVideo
CFGGuider
LTXVImgToVideoInplace
LTXVConcatAVLatent
SamplerCustomAdvanced
LTXVSeparateAVLatent
LTXVLatentUpsampler
LTXVCropGuides
ComfySwitchNode
VAEDecode
LTXVAudioVAEDecode
CreateVideo
SaveVideo
This workflow allows you to generate video with audio using any reference image, thanks to the new LTX 2.3 model and its official distilled LoRA.
Only native nodes are being used, organised in a way to encourage learning and exploration without the need to browse subgraphs.
Video tutorial (original audio in pt-BR, auto dub available):
Related links:
Read more
N