Instructions to use Lightricks/LTX-2.3-22b-IC-LoRA-Cross-Eyed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lightricks/LTX-2.3-22b-IC-LoRA-Cross-Eyed with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2.3", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Lightricks/LTX-2.3-22b-IC-LoRA-Cross-Eyed") prompt = "A man with short gray hair plays a red electric guitar." output = pipe(prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
You need to agree to share your contact information to access this model
By clicking "Agree and Access" you acknowledge the Privacy Policy and consent to receive offers and updates. You can unsubscribe at any time.
Log in or Sign Up to review the conditions and access this model content.
LTX-2.3 22B IC-LoRA CROOKED
IC-LoRA adapter for LTX-2 that transforms close-up portrait videos from straight eyes to permanent convergent strabismus (inward-turned / crossed eyes), while preserving facial expression, head movement, lighting, and camera framing.
Model Details
- Base model:
ltx2.3-20b-20k-step-2362000-v4.safetensors(Lightricks LTX-2) - Type: IC-LoRA (video-to-video)
- Training steps: 3000
- LoRA rank / alpha: 32 / 32
- Resolution buckets:
960×544×49(landscape),544×960×49(portrait)
Requirements
This LoRA is an adapter, not a standalone model. You also need:
- Base checkpoint:
ltx2.3-20b-20k-step-2362000-v4.safetensors - Text encoder:
gemma-3-12b-it-qat-q4_0-unquantized - A reference video with straight eyes
Frame count must satisfy frames % 8 == 1 (e.g. 49, 145, 201). Use 544×960 for portrait clips.
Usage
LTX Trainer
cd LTX-2/packages/ltx-trainer
uv run python scripts/inference.py \
--checkpoint path/to/ltx2.3-20b-20k-step-2362000-v4.safetensors \
--text-encoder-path path/to/gemma-3-12b-it-qat-q4_0-unquantized \
--lora-path path/to/lora_weights_step_03000.safetensors \
--reference-video path/to/straight_eye_clip.mp4 \
--prompt "A close-up portrait video of a man with permanent severe convergent strabismus. Both eyes are continuously turned inward toward the nose throughout the shot. The subject maintains natural facial expression, head movement, lighting, and camera framing." \
--negative-prompt "normal eyes, straight eyes, corrected eyes, gaze correction, blurry, jittery" \
--width 960 --height 544 \
--num-frames 49 \
--num-inference-steps 30 \
--guidance-scale 4.0 \
--stg-scale 1.0 --stg-blocks 29 --stg-mode stg_v \
--skip-audio \
--output crooked.mp4
ComfyUI
- Place
lora_weights_step_03000.safetensorsinComfyUI/models/loras/. - Load the matching LTX 2.3 base checkpoint.
- Use an IC-LoRA / video-to-video workflow with a reference video input.
Reference workflows: LTX-2 repository.
Example Prompts
Positive:
A close-up portrait video of a man with permanent severe convergent strabismus. Both eyes are continuously turned inward toward the nose throughout the shot. The subject maintains natural facial expression, head movement, lighting, and camera framing.
Negative:
worst quality, inconsistent motion, blurry, jittery, distorted, normal eyes, straight eyes, corrected eyes, gaze correction
License
This model inherits the license of the base model (Lightricks LTX-2).
- Downloads last month
- 78
Model tree for Lightricks/LTX-2.3-22b-IC-LoRA-Cross-Eyed
Base model
Lightricks/LTX-2.3