finetrainers/CogVideoX-1.5-crush-smol-v0

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 colorful jelly beans, flattening them 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.

This is a LoRA fine-tune of the THUDM/CogVideoX1.5-5b 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:

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.