CoolFace
Modelpublic

naomiKenKorem/LTXV_13B_LoRA_smpl

sourceHugging Faceotherupdated 1y agoView on Hugging Face
0likes18downloads
Model Card

LTXV13BLoRA_smpl

This is a fine-tuned version of `LTXV_13B_097_DEV` trained on custom data.

Model Details

  • —Base Model: `LTXV_13B_097_DEV`
  • —Training Type: LoRA fine-tuning
  • —Training Steps: 4000
  • —Learning Rate: 0.0002
  • —Batch Size: 1

Sample Outputs

[image]<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>people dancing</details>[image]<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>a woman talking</details>[image]<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>a man skiing</details>

Usage

This model is designed to be used with the LTXV (Lightricks Text-to-Video) pipeline.

🔌 Using Trained LoRAs in ComfyUI

In order to use the trained lora in comfy:

  1. 1.Copy your comfyui trained LoRA weights (comfyui..safetensors file) to the models/loras folder in your ComfyUI installation.
  2. 2.In your ComfyUI workflow:
  3. 3.Add the "LTXV LoRA Selector" node to choose your LoRA file
  4. 4.Connect it to the "LTXV LoRA Loader" node to apply the LoRA to your generation

You can find reference Text-to-Video (T2V) and Image-to-Video (I2V) workflows in the official LTXV ComfyUI repository.

Example Prompts

Example prompts used during validation:

  • —people dancing
  • —a woman talking
  • —a man skiing

This model inherits the license of the base model (`LTXV_13B_097_DEV`).

Acknowledgments