FOFPred

import einops
import numpy as np
import torch
from diffusers import DiffusionPipeline
from PIL import Image

# Load pipeline with trust_remote_code
pipeline = DiffusionPipeline.from_pretrained(
    "Salesforce/FOFPred",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
).to("cuda")

# Run inference
results = pipeline(
    prompt="Moving the water bottle from right to left.",
    input_images=[Image.open("your_image.jpg")],
    width=256,
    height=256,
    num_inference_steps=1,
    num_images_per_prompt=4,
    frame_count=4,
    generator=torch.Generator(device="cuda").manual_seed(42),
    output_type="pt",
)

flow_frames = results.images  # [B, F, C, H, W]

output_tensor = flow_frames[0]  # [F, C, H, W]
output_np = pipeline.image_processor.pt_to_numpy(output_tensor)  # [F, H, W, C]
reshaped = einops.rearrange(output_np, "f h w c -> h (f w) c")
img = Image.fromarray((reshaped * 255).astype(np.uint8))
img.save("output_combined.png")