finetrainers/crush-smol-v0

Instalación y uso básico con Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("finetrainers/crush-smol-v0", dtype=torch.bfloat16, device_map="cuda")

prompt = "DIFF_crush A red candle is placed on a metal platform, and a large metal cylinder descends from above, flattening the candle as if it were under a hydraulic press. The candle is crushed into a flat, round shape, leaving a pile of debris around it."
image = pipe(prompt).images[0]

Inferencia recomendada cargando el transformador ajustado sobre CogVideoX-5b:

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

transformer = CogVideoXTransformer3DModel.from_pretrained(
    "finetrainers/crush-smol-v0", torch_dtype=torch.bfloat16
)

pipeline = DiffusionPipeline.from_pretrained(
    "THUDM/CogVideoX-5b", transformer=transformer, torch_dtype=torch.bfloat16
).to("cuda")

prompt = """
DIFF_crush A thick burger is placed on a dining table, and a large metal cylinder descends from above, crushing the burger as if it were under a hydraulic press. The bulb is crushed, leaving a pile of debris around it.
"""
negative_prompt = "inconsistent motion, blurry motion, worse quality, degenerate outputs, deformed outputs"

video = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_frames=81,
    height=512,
    width=768,
    num_inference_steps=50
).frames[0]

export_to_video(video, "output.mp4", fps=25)

Uso de la variante LoRA extraída:

from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video
import torch

pipeline = DiffusionPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16).to("cuda")
pipeline.load_lora_weights("finetrainers/cakeify-v0", weight_name="extracted_crush_smol_lora_64.safetensors")

prompt = """
DIFF_crush A thick burger is placed on a dining table, and a large metal cylinder descends from above, crushing the burger as if it were under a hydraulic press. The bulb is crushed, leaving a pile of debris around it.
"""
negative_prompt = "inconsistent motion, blurry motion, worse quality, degenerate outputs, deformed outputs"

video = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_frames=81,
    height=512,
    width=768,
    num_inference_steps=50
).frames[0]

export_to_video(video, "output_lora.mp4", fps=25)