---
license: other
pipeline_tag: image-to-image
---

# FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

[Paper](https://huggingface.co/papers/2610.36545) · [Project Page](https://lyne1.github.io/FrameForge-page/) · [Code](https://github.com/Lyne1/FrameForge)

FrameForge adapts the temporal priors of [HunyuanVideo 1.5](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5) for three conditional image-generation tasks with one model: **subject-driven generation**, **Canny-to-image generation**, and **instruction-guided image editing**. The condition image is treated as an earlier frame and the output image as a target frame. This repository provides the inference code for the three-expert, one-reasoning-latent configuration.

## Usage

For installation and checkpoint setup, please refer to the [GitHub repository](https://github.com/Lyne1/FrameForge). Run the commands from the repository root. Replace the example paths with your own reference or condition image, prepared at **512 × 512 pixels**. All three tasks generate a single **512 × 512** output image and use 50 denoising steps.

### Subject-driven generation

```bash
CUDA_VISIBLE_DEVICES=0 MODEL_PATH=./ckpts bash scripts/infer.sh \
  --lora_path ./checkpoints/pytorch_lora_weights.safetensors \
  --input_image ./inputs/subject.jpg \
  --reference_size 512 \
  --prompt "the dog playing on a beach" \
  --output_path ./outputs/subject.png \
  --num_inference_steps 50
```

### Canny-to-image generation

Pass a Canny edge map as the input image. The manuscript uses guidance scale `2.0` for this task:

```bash
CUDA_VISIBLE_DEVICES=0 MODEL_PATH=./ckpts bash scripts/infer.sh \
  --lora_path ./checkpoints/pytorch_lora_weights.safetensors \
  --input_image ./inputs/edges.png \
  --reference_size 512 \
  --prompt "A red car parked beside a lake at sunset" \
  --output_path ./outputs/canny.png \
  --num_inference_steps 50 --guidance_scale 2.0
```

### Instruction-guided image editing

Pass the source image and an editing instruction. The default guidance scale is `6.0`:

```bash
CUDA_VISIBLE_DEVICES=0 MODEL_PATH=./ckpts bash scripts/infer.sh \
  --lora_path ./checkpoints/pytorch_lora_weights.safetensors \
  --input_image ./inputs/edit.png \
  --reference_size 512 \
  --prompt "Change the sky to sunset while preserving the rest of the scene" \
  --output_path ./outputs/edited.png \
  --num_inference_steps 50
```

## Citation

```bibtex
@misc{lin2026frameforge,
  title  = {FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation},
  author = {Yijing Lin and Zhendong Mao and Mengqi Huang and Yuxin Wang and Yongdong Zhang},
  year   = {2026},
  eprint = {2610.36545},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url    = {https://arxiv.org/abs/2610.36545}
}
```

## License

This project is derived from HunyuanVideo 1.5 and retains its [Tencent Hunyuan Community License](https://github.com/Lyne1/FrameForge/blob/main/LICENSE) and [third-party notices](https://github.com/Lyne1/FrameForge/blob/main/NOTICE). Please review those terms before redistributing code or weights.