Quality LoRA617 MB16GB+ VRAMlora

LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors

LTX 2.3 OmniNFT RL LoRA (Kijai)

Reinforcement-learning quality LoRA for LTX 2.3 from the OmniNFT research line. Targets audio-video synchronization, lip-sync, motion coherence, and temporal stability rather than visual style — reported to cut audio-video DeSync from 0.569 to 0.269 on JavisBench. Place in models/loras/.

Released 2026-05-25 · Source: Kijai/LTX2.3_comfy (HuggingFace)RL-based quality LoRA from the OmniNFT research line. Improves audio-video sync (JavisBench DeSync 0.569 → 0.269), lip-sync, and temporal stability.

Download LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors

Direct HuggingFace download. 617 MB · Free.

Install path: ComfyUI/models/loras/ + LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors

No 16GB GPU? Try LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors online — free generation included

Skip the 617 MB download and ComfyUI setup. Generate a 6-second video using this exact model in your browser, ~30 seconds.

Try this model online — free →

Will this run on my GPU?

Minimum: 16GB VRAM.

GPUVRAMVerdict
RTX 3060 12GB12GBInsufficient VRAM
RTX 4060 Ti / 4070 (16GB)16GBTight fit
RTX 4070 Ti SUPER / 4080 (16GB)16GBTight fit
RTX 3090 (24GB)24GBComfortable
RTX 4090 (24GB)24GBComfortable
RTX 5090 / A6000 (32GB+)32GBComfortable

Recommendation: Add on top of your LTX 2.3 base model to improve audio-video sync and motion stability, especially for audio-conditioned and talking-head workflows. 617 MB BF16. As a behavioral (RL) LoRA it does not change your sampler steps/CFG the way a distillation LoRA does.

How to use LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors

  1. Download the file from HuggingFace.
  2. Place it in ComfyUI/models/loras/ inside your ComfyUI directory.
  3. Restart ComfyUI (or refresh the model list from the menu).
  4. Load a compatible workflow — see below.

Don't want to run this locally? Try LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors online with a free generation — no GPU, no install, ~30 seconds per clip.

ComfyUI says it can't find LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors?

Some published workflow JSONs reference this file under a custom subdirectory. If ComfyUI shows a "cannot find model" error and your workflow references one of these path-prefixed variants:

  • loras/LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors
  • ltx23\LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors

The prefix before the slash or backslash is a subdirectory the workflow author used. The actual file is the same LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors — you have two fixes:

  1. Create the matching subdirectory inside ComfyUI/models/loras/ and place the file there. Example: if the workflow references loras/LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors, create the corresponding subfolder under ComfyUI/models/loras/ and put LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors inside it.
  2. Or open the workflow JSON in a text editor and replace the prefixed string with just LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors. ComfyUI then resolves it directly from ComfyUI/models/loras/.

On Windows the separator is \, on macOS/Linux it is / — they refer to the same nested folder regardless of platform.

Common issues

ComfyUI doesn't see the file after I downloaded it

Make sure the file is in ComfyUI/models/loras/ (not a subfolder). Restart ComfyUI fully — the menu refresh sometimes misses new files. Filename must match exactly: LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors.

CUDA out of memory error when loading the model

LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors needs ~16GB VRAM minimum. If you're hitting OOM: • Enable Sequential Offloading in ComfyUI settings • Lower the resolution (768×512 instead of 1280×704) — both dimensions must be divisible by 32 • Reduce frame count (65 frames instead of 161) — must be 8n+1 • Use a smaller variant — see Related models below.

How do I apply this LoRA in ComfyUI?

Load it in a 'LoraLoader' node and connect it after your model loader. Pair this LoRA with the dev base model (not the distilled one) for the right behavior. LoRA strength 1.0 is the trained value — start there.

Free newsletter

Get notified when LTX 2.3 OmniNFT RL LoRA (Kijai) updates

Occasional updates on what's new in LTX 2.3 — new FP8 quants, LoRAs, IC-LoRA releases — with our hands-on verdict on whether they're worth re-downloading. No fixed cadence.

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

Related models