Hugging Face's logo

ltx-community
/
ltx2-compile-keytest

Text-to-Video
Diffusers
English
ltx-2
ltx-video
audio-video
Model card Files
xet
 Community
ltx2-compile-keytest / README.md
linoyts's picture
linoyts HF Staff
Upload folder using huggingface_hub
9d3e0f8 verified
preview code
|
Raw
History Blame Contribute Delete
2.99 kB
metadata 
tags:
  - ltx-2
  - ltx-video
  - text-to-video
  - audio-video
pinned: true
language:
  - en
license: other
pipeline_tag: text-to-video
library_name: diffusers

ltx2-compile-keytest

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

This is a IC-LoRA (in-context control) fine-tuned from ltx-2.3-22b-dev.safetensors on custom data.

Model Details

  • Base Model: ltx-2.3-22b-dev.safetensors
  • LoRA type: IC-LoRA (in-context control)
  • Training Type: LoRA fine-tuning
  • Training Steps: 300
  • Learning Rate: 0.0002
  • 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 LTX2InContextPipeline
from diffusers.pipelines.ltx2.export_utils import encode_video
from diffusers.pipelines.ltx2.utils import DEFAULT_NEGATIVE_PROMPT

pipe = LTX2InContextPipeline.from_pretrained(
    "diffusers/LTX-2.3-Diffusers", torch_dtype=torch.bfloat16
)
pipe.enable_model_cpu_offload()

# Load this LoRA
pipe.load_lora_weights("ltx-community/ltx2-compile-keytest", weight_name="lora_weights_step_00300.safetensors", adapter_name="lora")
pipe.set_adapters("lora", 1.0)

video, audio = pipe(
    prompt="<your prompt>",
    negative_prompt=DEFAULT_NEGATIVE_PROMPT,
    # IC-LoRA is reference-conditioned — pass your control video via reference_conditions:
    # reference_conditions=[...],  # see the LTX-2 diffusers docs for the condition object
    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