LTX 2.3 ComfyUI Workflow Configurator

Select your model, resolution, and generation mode — we'll recommend the right official workflow and tell you exactly which nodes to update. All workflows require taeltx2_3.safetensors (VAE) or comfy_gemma_3_12B_it.safetensors — download models here first.

Available: ltx-2.3_t2v_i2v_single_stage_distilled_full.json · ltx-2.3_t2v_i2v_two_stage_distilled.json · ltx-2.3_iclora_union_control_distilled.json · ltx-2.3_iclora_motion_track_distilled.json · ltx-2.3_iclora_hdr_distilled.json

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)

Official Workflow Templates

Download official LTX 2.3 ComfyUI workflow JSON files from Lightricks. Drag any .json file into ComfyUI to load it instantly.

Download Workflows ↓How to Choose ↓

T2V / I2V Single Stage Distilled

Start here. Text-to-video and image-to-video in one workflow using the distilled model. Fastest generation, works on 16GB VRAM with FP8.

T2VI2VDistilledBeginner16GB+8 steps, CFG=1

Requires:

  • ✓taeltx2_3.safetensors (VAE)
  • ✓ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensors (16GB) or ltx-2.3-22b-distilled-1.1.safetensors (32GB)
LTX-2.3_T2V_I2V_Single_Stage_Distilled_Full.jsonDownload JSON →

T2V / I2V Two Stage Distilled

Two-stage pipeline: generate at low resolution then upscale 2× with the spatial upscaler. Better quality at higher resolution.

T2VI2VDistilledUpscalerHigh-Res16GB+8 steps + upscale

Requires:

  • ✓taeltx2_3.safetensors (VAE)
  • ✓ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensors (16GB) or ltx-2.3-22b-distilled-1.1.safetensors (32GB)
  • ✓ltx-2.3-spatial-upscaler-x2-1.0.safetensors
LTX-2.3_T2V_I2V_Two_Stage_Distilled.jsonDownload JSON →

ICLoRA Union Control Distilled

Image-conditioned LoRA with union control net. Apply a LoRA and control signal simultaneously for precise video generation from a reference image.

ICLoRALoRAControlDistilledAdvanced16GB+8 steps, CFG=1

Requires:

  • ✓taeltx2_3.safetensors (VAE)
  • ✓ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensors (16GB) or ltx-2.3-22b-distilled-1.1.safetensors (32GB)
  • ✓A compatible LTX 2.3 LoRA file
LTX-2.3_ICLoRA_Union_Control_Distilled.jsonDownload JSON →

ICLoRA Motion Track Distilled

Motion tracking with ICLoRA. Define motion trajectories to control how objects or subjects move through the generated video.

ICLoRALoRAMotionDistilledAdvanced16GB+8 steps, CFG=1

Requires:

  • ✓taeltx2_3.safetensors (VAE)
  • ✓ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensors (16GB) or ltx-2.3-22b-distilled-1.1.safetensors (32GB)
  • ✓A compatible LTX 2.3 LoRA file
LTX-2.3_ICLoRA_Motion_Track_Distilled.jsonDownload JSON →

ICLoRA HDR Distilled

Generate HDR video with enhanced dynamic range. Uses the ICLoRA HDR LoRA and Gemma 3 text encoder for better color grading and highlight/shadow detail.

ICLoRAHDRLoRADistilledAdvanced16GB+8 steps, CFG=1

Requires:

  • ✓ltx-2.3-22b-dev.safetensors
  • ✓comfy_gemma_3_12B_it.safetensors (text encoder)
  • ✓ltx-2.3-22b-ic-lora-hdr-0.9.safetensors
  • ✓ltx-2.3-22b-distilled-lora-384-1.1.safetensors
LTX-2.3_ICLoRA_HDR_Distilled.jsonDownload JSON →
How to Choose

Which workflow should I use?

First time with LTX 2.3?

→ Single Stage Distilled

Fastest setup. Works on 16GB VRAM with FP8. T2V + I2V in one workflow.

Want higher resolution output?

→ Two Stage Distilled

Generate at low res, then upscale 2× with the spatial upscaler model.

Have a LTX 2.3 LoRA?

→ ICLoRA Union Control

Apply LoRA + control signal together. Use with a reference image.

Want to control motion paths?

→ ICLoRA Motion Track

Draw motion trajectories to control how subjects move in the video.

Want HDR / cinematic dynamic range?

→ ICLoRA HDR

Uses the HDR LoRA + Gemma 3 encoder for enhanced highlights and shadows.

Custom Workflow Generator

Generate a personalized ComfyUI LTX 2.3 workflow JSON with your own prompt, resolution, VRAM, and model settings.