Hugging Face's logo

Lightricks
/
LTX-2.3-22b-IC-LoRA-Cross-Eyed

Text-to-Video
Diffusers
English
ltx-2
ltx-video
ic-lora
video-to-video
lora
Model card Files
xet
 Community
2
LTX-2.3-22b-IC-LoRA-Cross-Eyed / README.md
art-alex's picture
art-alex
Update README.md
0c10dc4 verified
preview code
|
Raw
History Blame Contribute Delete
3.66 kB
metadata 
base_model:
  - Lightricks/LTX-2.3
base_model_relation: adapter
license: other
license_name: ltx-2-community-license
license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE
language:
  - en
tags:
  - ltx-2
  - ltx-video
  - ic-lora
  - video-to-video
  - lora
pipeline_tag: text-to-video
library_name: diffusers
extra_gated_description: >-
  By clicking "Agree and Access" you acknowledge the [Privacy
  Policy](https://static.lightricks.com/legal/Privacy%20Policy%20-%20LTX%20Platform.pdf) 
  and consent to receive offers and updates. You can unsubscribe at any time.
extra_gated_button_content: Agree and Access

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:

  1. Base checkpoint: ltx2.3-20b-20k-step-2362000-v4.safetensors
  2. Text encoder: gemma-3-12b-it-qat-q4_0-unquantized
  3. 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

  1. Place lora_weights_step_03000.safetensors in ComfyUI/models/loras/.
  2. Load the matching LTX 2.3 base checkpoint.
  3. 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

See the LTX-2-community-license for full terms.

Acknowledgments