---
base_model:
- THUDM/CogVideoX1.5-5b
datasets: finetrainers/crush-smol
library_name: diffusers
license: other
license_link: https://huggingface.co/THUDM/CogVideoX1.5-5b/blob/main/LICENSE
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-3000-0-2-PIKA_CRUSH-A-red-toy-car-.mp4
- text: >-
    PIKA_CRUSH A large metal cylinder is seen pressing down on a pile of colorful jelly beans, flattening them as if they were under a hydraulic press.
  output:
    url: final-3000-0-2-PIKA_CRUSH-A-large-metal-.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-3000-1-2-PIKA_CRUSH-A-large-metal-.mp4
tags:
- text-to-video
- diffusers-training
- diffusers
- cogvideox
- cogvideox-diffusers
- template:sd-lora
---

<Gallery />

This is a LoRA fine-tune of the [THUDM/CogVideoX1.5-5b](https://huggingface.co/THUDM/CogVideoX1.5-5b) model on the
[finetrainers/crush-smol](https://huggingface.co/datasets/finetrainers/crush-smol) dataset.

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

> [!IMPORTANT]
> This is an experimental checkpoint and its poor generalization is well-known.

Inference code:

```py
from diffusers import CogVideoXTransformer3DModel, DiffusionPipeline 
from diffusers.utils import export_to_video
import torch 

pipeline = DiffusionPipeline.from_pretrained(
    "THUDM/CogVideoX1.5-5b", torch_dtype=torch.bfloat16
).to("cuda")
pipeline.load_lora_weights("finetrainers/CogVideoX-1.5-crush-smol-v0", adapter_name="cogvideox-lora")
pipeline.set_adapters("cogvideox-lora", 0.9)

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.
"""
negative_prompt = "inconsistent motion, blurry motion, worse quality, degenerate outputs, deformed outputs"

video = pipeline(
    prompt=prompt, 
    negative_prompt=negative_prompt, 
    num_frames=81, 
    height=480,
    width=768,
    num_inference_steps=50
).frames[0]
export_to_video(video, "output.mp4", fps=25)
```

Training logs are available on WandB [here](https://wandb.ai/aryanvs/finetrainers-cogvideox?nw=nwuseraryanvs).