Run LTX 2.5 & LTX 2.3 in ComfyUI — Match Your VRAM, Fix Missing Files, Generate the Workflow
Stuck on a missing taeltx2_3.safetensors, an out-of-memory error, or the wrong checkpoint for your GPU? Pick a model family and your VRAM — LTX 2.5's gated Gemma 4 files need 24GB+ unless you use the GGUF path, LTX 2.3's FP8 fits 16GB — get the exact files you need, and generate a ready-to-import ComfyUI workflow JSON for LTX 2.3 in under 2 minutes. T2V, I2V, LoRA, and spatial upscaler all supported.
VRAM Adapter
Select a model family and your GPU VRAM to see recommended LTX models:
Checkpoints for 16GB
LTX-2.5-Distilled-Q3_K_S.ggufLTX-2.5-Distilled-Q4_K_M.ggufRequired & optional components
gemma4-12b-with-proj-ltx-2.5-bf16.safetensorsgemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensorsltx-2.5-video-vae-bf16.safetensorsLTX 2.5 & LTX 2.3 Model Downloads
LTX 2.3 FP8 (16GB) and official distilled & dev (24–32GB), plus LTX 2.5's gated Gemma 4 + INT8 convrot files (24GB+) or the community GGUF path for 16GB.
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.
LTX 2.3 Workflow Configurator
LTX 2.3 onlyAnswer a few questions — we'll pick the right LTX 2.3 workflow, model files, and node settings for your GPU. Looking for LTX 2.5? See the LTX 2.5 setup guide instead — its official workflow files aren't verified yet, so this builder doesn't cover it.
⚠ RTX 30xx? The selected FP8 model needs RTX 40xx+ hardware. Use the int8_convrot variant (fastest on Ampere INT8 cores), or mxfp8_block32 / BF16 instead.
Models for your GPU
Transformer · 768x512
ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensorsText encoder (Gemma 3 12B)
gemma_3_12B_it_fp4_mixed.safetensorsFP8 transformer (~25 GB) + FP4 Gemma (9.5 GB)
Recommended workflow
T2V / I2V Single Stage Distilled
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
Node settings after loading the workflow
ltx-2.3-22b-distilled-1.1_transformer_only_fp8_scaled.safetensorsLTX23_audio_vae_bf16.safetensorsPlace in models/checkpoints/
gemma_3_12B_it_fp4_mixed.safetensorsyour-image.pngDrag your source image here
768 / 512Both must be divisible by 32
121Must be 8n+1 (65, 97, 121…)
241Keep at 1.0 — raising CFG doubles VRAM with no quality benefit
euler_ancestral_cfg_ppVerified from official JSON
ltx-2.3-22b-distilled-lora-384-1.1.safetensorsstrength 0.5 — must be v1.1 (official JSON ships v1.0 by mistake)
LTX Insider
Occasional updates when notable LTX 2.5 or LTX 2.3 models drop — new 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 2.5 on HuggingFace →
Official model weights by Lightricks (gated)
LTX 2.3 on HuggingFace →
Official model weights by Lightricks
ComfyUI-LTXVideo →
Official ComfyUI nodes & example workflows
Kijai FP8 Models (LTX 2.3) →
FP8 quantized variants for 16GB VRAM
Abiray GGUF Quants (LTX 2.5) →
Community GGUF quants 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