README.md

metadata

base_model:
  - Lightricks/LTX-Video
  - a-r-r-o-w/LTX-Video-diffusers
datasets: finetrainers/crush-smol
library_name: diffusers
license: other
license_link: https://huggingface.co/Lightricks/LTX-Video/blob/main/License.txt
widget:
  - text: >-
      PIKA_CRUSH A red toy car is being crushed by a large hydraulic press,
      which is flattening objects as if they were under a hydraulic press.
    output:
      url: final-7500-0-2-PIKA_CRUSH-A-red-toy-car-.mp4
  - text: >-
      PIKA_CRUSH A large metal cylinder is seen pressing down on a pile of Oreo
      cookies, flattening them as if they were under a hydraulic press.
    output:
      url: final-7500-0-2-PIKA_CRUSH-A-large-metal-.mp4
  - text: >-
      PIKA_CRUSH A red toy car is being crushed by a large hydraulic press,
      which is flattening objects as if they were under a hydraulic press.
    output:
      url: final-7500-1-2-PIKA_CRUSH-A-red-toy-car-.mp4
tags:
  - text-to-video
  - diffusers-training
  - diffusers
  - template:sd-lora
  - ltx-video

Prompt

PIKA_CRUSH A red toy car is being crushed by a large hydraulic press, which is flattening objects as if they were under a hydraulic press.

Prompt

PIKA_CRUSH A large metal cylinder is seen pressing down on a pile of Oreo cookies, flattening them as if they were under a hydraulic press.

Prompt

PIKA_CRUSH A red toy car is being crushed by a large hydraulic press, which is flattening objects as if they were under a hydraulic press.

This is a LoRA fine-tune of the Lightricks/LTX-Video model on the finetrainers/crush-smol dataset.

Code: https://github.com/a-r-r-o-w/finetrainers

This is an experimental checkpoint and its poor generalization is well-known.

Inference code:

import torch
from diffusers import LTXPipeline
from diffusers.utils import export_to_video

pipe = LTXPipeline.from_pretrained(
    "Lightricks/LTX-Video", torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights("my-awesome-name/my-awesome-lora", adapter_name="ltxv-lora")
pipe.set_adapters(["ltxv-lora"], [0.9])

video = pipe("<my-awesome-prompt>").frames[0]
export_to_video(video, "output.mp4", fps=8)

Training logs are available on WandB here.