Generate a video with accompanying generated audio from a text description. Describe subjects, appearance, actions over time, camera movement, and desired sounds, dialogue, or singing. No uploaded image or audio is required. The selected output combines the decoded imagery and audio into one video; MP4 is the default container.
Workflow details
Perfil de ejecución
Fuentes
1 fuenteHover nodes for Pipe controls
Core
Primary Pipe surface
Scene and sound
CLIPTextEncode
Negative prompt
CLIPTextEncode
Output size
EmptyImage
Video length
PrimitiveInt
Video output
SweetTeaPreviewVideo
Extended
Additional surfaced controls
Video timing
PrimitiveFloat
Audio timing
PrimitiveInt
Initial camera guidance
LoraLoaderModelOnly
Refinement camera guidance
LoraLoaderModelOnly
Initial randomness
RandomNoise
Initial guidance
CFGGuider
Initial sampling
LTXVScheduler
Initial sampler
KSamplerSelect
Refinement randomness
RandomNoise
Refinement guidance
CFGGuider
Refinement sampler
KSamplerSelect
Video precision
CreateVideo
Distilled refinement adapter
LoraLoaderModelOnly
Refinement noise schedule
ManualSigmas
Remaining hardware or download-size estimates are not available yet.
failure · stage is decode
tile_size to 256 on node 109.Smaller tiles can change seams and decode work; inspect the output. Only the VAE decode stage changes. Model loading and denoising memory are unaffected.
Requisitos
gemma_3_12B_it_fp4_mixed.safetensors
Archivo sin verificarText encoder · Hugging Face · Comfy-Org/ltx-2 · Ltx 2
Text encoder · Hugging Face · Lightricks/LTX-2 · LTX-2 Model Checkpoint
ltx-2-19b-distilled-lora-384.safetensors
No resueltoLoRA · Hugging Face · Lightricks/LTX-2
ltx-2-19b-lora-camera-control-dolly-left.safetensors
Archivo sin verificarLoRA · Hugging Face · Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Left · LTX 2 19b LoRA Camera Control Dolly Left
ltx-2-spatial-upscaler-x2-1.0.safetensors
Archivo sin verificarUpscaler · Hugging Face · Lightricks/LTX-2 · LTX 2
Paquete de nodos · GitHub · tea-time-labs/sweet-tea-nodes