---
license: apache-2.0
library_name: diffusers
pipeline_tag: image-to-image
tags:
- optical-flow prediction
- motion prediction
- diffusion
---

# FOFPred: Language-Driven Future Optical Flow Prediction

**FOFPred** is a diffusion-based model that predicts future optical flow from a single image guided by natural language instructions. Given an input image and a text prompt describing a desired action (e.g., *"Moving the water bottle from right to left"*), FOFPred generates 4 sequential optical flow frames showing how objects would move.

## Usage

```python
import torch
from fofpred.pipelines.fofpred.pipeline_fofpred import FOFPredPipeline
from fofpred.schedulers.scheduling_flow_match_euler_discrete import FlowMatchEulerDiscreteScheduler
from PIL import Image

pipeline = FOFPredPipeline.from_pretrained(
    "Salesforce/FOFPred",
    torch_dtype=torch.bfloat16,
).to("cuda")

pipeline.scheduler = FlowMatchEulerDiscreteScheduler()

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]
```

## Architecture

| Component | Model |
|-----------|-------|
| **V-LLM** | Qwen2.5-VL-3B-Instruct |
| **DiT** | OmniGen2Transformer3DModel |
| **VAE** | FLUX.1-dev AutoencoderKL |
| **Scheduler** | FlowMatchEulerDiscreteScheduler |

## Acknowledgements

- [OmniGen2](https://github.com/VectorSpaceLab/OmniGen2)
- [Qwen2.5-VL](https://huggingface.co/Qwen/Qwen2.5-VL)
- [Flux VAE](https://huggingface.co/black-forest-labs/FLUX.1-dev)

## License

Apache 2.0 — Copyright (c) 2025 Salesforce, Inc.