CoolFace
Modelpublic

charlied98/ltxv_2b_lora_soft_draw_v1

sourceHugging Faceotherupdated 1y agoView on Hugging Face
0likes12downloads
Model Card

ltxv2blorasoftdraw_v1

This is a fine-tuned version of `LTXV_2B_0.9.6_DEV` trained on custom data.

Model Details

  • —Base Model: `LTXV_2B_0.9.6_DEV`
  • —Training Type: LoRA fine-tuning
  • —Training Steps: 3000
  • —Learning Rate: 0.0002
  • —Batch Size: 2

Sample Outputs

[image]<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>a snowy village square during a gentle snowfall, with twinkling holiday lights, warmly dressed people strolling past market stalls, and a large decorated tree at the center</details>[image]<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>a deep underwater scene with shafts of light breaking through the surface, illuminating coral reefs and schools of colorful fish swimming gracefully through the blue depths.</details>[image]<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>a dramatic cliffside overlooking a stormy sea, where crashing waves slam against the rocks below, and dark clouds churn above, hinting at an approaching tempest.</details>[image]<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>a peaceful rural farm at sunrise, with golden light spilling across open fields, a red barn in the distance, and a few grazing animals starting their day.</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:

  • —a snowy village square during a gentle snowfall, with twinkling holiday lights, warmly dressed people strolling past market stalls, and a large decorated tree at the center
  • —a deep underwater scene with shafts of light breaking through the surface, illuminating coral reefs and schools of colorful fish swimming gracefully through the blue depths.
  • —a dramatic cliffside overlooking a stormy sea, where crashing waves slam against the rocks below, and dark clouds churn above, hinting at an approaching tempest.
  • —a peaceful rural farm at sunrise, with golden light spilling across open fields, a red barn in the distance, and a few grazing animals starting their day.

This model inherits the license of the base model (`LTXV_2B_0.9.6_DEV`).

Acknowledgments