LTX 2.3 for ComfyUI — Model Downloads, Workflow Templates & Online Image-to-Video

Download LTX 2.3 models with direct links — taeltx2_3.safetensors VAE, FP8 quantized (16GB VRAM), and official checkpoints (32GB). Generate ComfyUI workflow JSON instantly. Supports T2V, I2V, LoRA, and spatial upscaler.

✓ taeltx2_3.safetensors✓ FP8 16GB VRAM✓ Direct Links✓ ComfyUI Ready
▶ Try LTX 2.3 Online — FreeDownload Models →

VRAM Adapter

Select your GPU VRAM to see recommended LTX 2.3 models:

Download

Checkpoints for 16GB

LTX 2.3 Distilled 1.1 FP8 (Kijai)16GB Best
ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensors

Best choice for 16GB VRAM. Latest v1.1 FP8 distilled. Requires RTX 40xx+ for fp8 matmuls.

LTX 2.3 Distilled 1.1 LoRA (Kijai)16GB LoRA
ltx-2.3-22b-distilled-1.1_lora-dynamic_fro09_avg_rank_111_bf16.safetensors

Pair with the dev FP8 model. Load as LoRA in ComfyUI models/loras/.

LTX 2.3 Distilled 1.1 LoRA — fro90_ceil72 cond-safe (TenStrip)🔥 NewI2V LoRA
ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors

Pair with the dev FP8 model when running image-to-video or other input-conditioned workflows. Use the standard Kijai dynamic-rank LoRA for T2V instead.

Required & optional components

Spatial Upscaler x1.5
ltx-2.3-spatial-upscaler-x1.5-1.0.safetensors

Use when x2 upscale is too aggressive. Gentler upscaling option.

Temporal Upscaler x2
ltx-2.3-temporal-upscaler-x2-1.0.safetensors

Optional. Use to double frame count (e.g. 65→129 frames) for smoother motion.

Spatial Upscaler x2 v1.1v1.1
ltx-2.3-spatial-upscaler-x2-1.1.safetensors

Updated upscaler. Prefer over v1.0 for better upscaling quality.

LTX 2.3 Model Downloads

All checkpoints for ComfyUI — FP8 (16GB), official distilled & dev (24–32GB), plus the required taeltx2_3.safetensors VAE.

Download Models →How to Choose →

LTX 2.3 ComfyUI Workflow JSON

Official workflow JSON files from Lightricks — T2V, I2V, two-stage upscaler, ICLoRA motion tracking. Drag into ComfyUI to load.

Download Workflows →How to Choose →

ComfyUI Workflow Configurator

Answer a few questions — we'll pick the right workflow, model files, and node settings for your GPU.

⚠ RTX 30xx? The selected FP8 model needs RTX 40xx+ hardware. Use the mxfp8_block32 variant or BF16 instead.

High+: 24 GB

Models for your GPU

Transformer · 768x512

ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensors

Text encoder (Gemma 3 12B)

gemma_3_12B_it_fp4_mixed.safetensors

FP8 transformer (~25 GB) + FP4 Gemma (9.5 GB)

Recommended workflow

T2V / I2V Single Stage Distilled

Download JSON →

Standard I2V workflow — attach your image to LTXVImgToVideoConditioning. Generates video + synchronized audio in one pass.

!IMPORTANT: After loading the JSON, update LoraLoaderModelOnly → ltx-2.3-22b-distilled-lora-384-1.1.safetensors. The official JSON ships v1.0 refs — v1.0 LoRA on v1.1 base causes stiff motion and color drift.

Required files

  • ✓ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensors
  • ✓taeltx2_3.safetensors
  • ✓LTX23_audio_vae_bf16.safetensors
  • ✓gemma_3_12B_it_fp4_mixed.safetensors
  • ✓ltx-2.3-22b-distilled-lora-384-1.1.safetensors
Download models →

Node settings after loading the workflow

CheckpointLoaderSimple→ckpt_name:ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensors
LTXVAudioVAELoader→model_name:LTX23_audio_vae_bf16.safetensors

Place in models/checkpoints/

LTXAVTextEncoderLoader→model_name:gemma_3_12B_it_fp4_mixed.safetensors
LTXVImgToVideoConditioning→image:your-image.png

Drag your source image here

EmptyLTXVLatentVideo→width / height:768 / 512

Both must be divisible by 32

EmptyLTXVLatentVideo→length:121

Must be 8n+1 (65, 97, 121…)

LTXVConditioning→frame_rate:24
CFGGuider→cfg:1

Keep at 1.0 — raising CFG doubles VRAM with no quality benefit

KSamplerSelect→sampler_name:euler_ancestral_cfg_pp

Verified from official JSON

LoraLoaderModelOnly→lora_name:ltx-2.3-22b-distilled-lora-384-1.1.safetensors

strength 0.5 — must be v1.1 (official JSON ships v1.0 by mistake)

Free newsletter

LTX Insider

Occasional updates when notable LTX 2.3 models drop — Kijai FP8 quants, Lightricks releases, IC-LoRAs. No fixed cadence, no spam. Unsubscribe in one click.

No spam. Sent occasionally when there's real news. Unsubscribe in one click.

Official Resources

LTX 2.3 on HuggingFace →

Official model weights by Lightricks

ComfyUI-LTXVideo →

Official ComfyUI nodes & example workflows

Kijai FP8 Models →

FP8 quantized variants for 16GB VRAM

LTX-Video GitHub →

Official LTX-Video model repository

ComfyUI →

Node-based UI for running diffusion models

ComfyUI Manager →

Install LTXVideo nodes via Manager