yaoi_NEW_LTX_4k

yaoi_NEW_LTX_4k

Trained with the LTX LoRA Trainer — powered by LTX-2.

This is a Image-to-Video LoRA fine-tuned from ltx-2.3-22b-dev.safetensors on custom data.

Model Details

• Base Model: ltx-2.3-22b-dev.safetensors
• LoRA type: Image-to-Video LoRA
• Training Type: LoRA fine-tuning
• Training Steps: 4000
• Learning Rate: 0.0001
• Batch Size: 1

Sample Outputs

Usage

🧨 Diffusers

LTX-2.3 support is currently on the diffusers main branch: pip install git+https://github.com/huggingface/diffusers.git

import torch
from diffusers import LTX2ImageToVideoPipeline
from diffusers.utils import load_image
from diffusers.pipelines.ltx2.export_utils import encode_video
from diffusers.pipelines.ltx2.utils import DEFAULT_NEGATIVE_PROMPT

pipe = LTX2ImageToVideoPipeline.from_pretrained(
    "diffusers/LTX-2.3-Diffusers", torch_dtype=torch.bfloat16
)
pipe.enable_model_cpu_offload()

# Load this LoRA
pipe.load_lora_weights("Hinorix/yaoi_NEW_LTX_4k", weight_name="lora_weights_step_04000.safetensors", adapter_name="lora")
pipe.set_adapters("lora", 1.0)

video, audio = pipe(
    prompt="<your prompt>",
    negative_prompt=DEFAULT_NEGATIVE_PROMPT,
    image=load_image("first_frame.png"),
    width=768, height=512, num_frames=49, frame_rate=25.0,
    num_inference_steps=30, guidance_scale=4.0,
    output_type="np", return_dict=False,
)
encode_video(video[0], fps=25.0, output_path="output.mp4")

For the full reference implementation and ComfyUI workflows, see the official LTX-2 repository.

🔌 Using Trained LoRAs in ComfyUI

In order to use the trained LoRA in ComfyUI, follow these steps:

1. Copy your trained LoRA checkpoint (.safetensors file) to the models/loras folder in your ComfyUI installation.
2. In your ComfyUI workflow:
   • Add the "Load LoRA" node to choose your LoRA file
   • Connect it to the "Load Checkpoint" node to apply the LoRA to the base model

You can find reference Text-to-Video (T2V) and Image-to-Video (I2V) workflows in the official LTX-2 repository.

Example Prompts

This model inherits the license of the base model (ltx-2.3-22b-dev.safetensors).

Acknowledgments

• Base model: Lightricks
• Trainer: LTX-2