Skip to content

Loading

Make images and video without living inside the AI toolchain.

A local-first workspace for turning ComfyUI workflows into tools you can use, understand, and reuse.

Product

Download Studio Resources Workflow Doctor Agent Access

Learn

Docs FAQ Updates

Connect

Feedback Privacy Terms Desktop EULA Acceptable use Report content

© 2026 Tea Time Labs

Local AI creation, organized.

Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗

DiscoverResources

My Desk Download StudioLanguage

LTX 2.3 video with generated audio | ST Studio

Resources/LTX 2.3 video with generated audio

Published version

Version details

Add to Studio keeps this exact version. Updates won’t replace your saved copy.

PipeListedHosted

LTX 2.3 video with generated audio

Generate a video with audio from a text description using LTX 2.3. No image, video, or audio upload is required.

Generate a video with audio from a text description using LTX 2.3. No image, video, or audio upload is required.

Workflow details

FamilyLTX-VideoResolution1024x1024Estimated VRAMNot yet characterizedPublisherSweet Tea AutomationUpdatedOct 22Bgrade

Runtime profile

Publisher: Sweet Tea Automation
Status: Listed
Version

Sources

1 source

Sweet TeaSource

Checking published version…

Updated

Oct 22, 2026

Hover nodes for Pipe controls

Core

Primary Pipe surface

Scene and sound prompt

CLIPTextEncode

Negative prompt

CLIPTextEncode

Output size

EmptyImage

Duration

easy int

Extended

Additional surfaced controls

Frame rate

easy int

Motion timing

LTXVConditioning

Distillation LoRA

LoraLoaderModelOnly

Generation randomization

RandomNoise

Generation guidance

CFGGuider

Generation sampling

KSamplerSelect

Refinement randomization

RandomNoise

Refinement guidance

CFGGuider

Refinement sampling

KSamplerSelect

Video precision

CreateVideo

Video output

SweetTeaPreviewVideo

Output

Generation noise schedule

ManualSigmas

Refinement noise schedule

ManualSigmas

What you need

Model files: 1.7 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Output

Sweet Tea Preview Video · video

Requirements

Models

7

gemma_3_12B_it_fp4_mixed.safetensors.safetensors
Not resolved
Text encoder · Unknown
ltx-2-spatial-upscaler-x2-1.0.safetensors
File unverified
Upscaler · Hugging Face · Lightricks/LTX-2 · LTX 2

ltx-2.3_text_projection_bf16.safetensors

Not resolved

Text encoder · Unknown

ltx-2.3-22b-dev_audio_vae.safetensors

Found

VAE · 348 MB · SAFETENSORS · Unknown

ltx-2.3-22b-dev_video_vae.safetensors

Found

VAE · 1.35 GB · SAFETENSORS · Unknown

ltx-2.3-22b-distilled-lora-dynamic_fro09_avg_rank_105_bf16.safetensors

Not resolved

LoRA · Unknown

ltx-2.3-22b-distilled-UD-Q4_K_M.gguf

Not resolved

Checkpoint · Unknown

Node packs

5

comfyui-easy-use
Found
Node pack · Registry
ComfyUI-GGUF
Possible
Node pack · Registry
comfyui-kjnodes
Found
Node pack · Registry
comfyui-mixlab-nodes
Possible
Node pack · Registry
tea-time-labs/sweet-tea-nodes
Found
Node pack · GitHub · tea-time-labs/sweet-tea-nodes