| --- |
| library_name: transformers |
| pipeline_tag: image-text-to-text |
| tags: |
| - image-forensics |
| - image-manipulation-detection |
| - visual-tool-use |
| - qwen3-vl |
| --- |
| |
| # ForgeryVCR |
|
|
| ForgeryVCR is a visual-centric image-forensics agent built on |
| Qwen3-VL-4B-Instruct. It actively calls ELA, FFT, NPP, and Zoom-In tools, |
| classifies an image as authentic or tampered, and localizes manipulated regions |
| with bounding boxes. |
|
|
| The released merged GRPO checkpoint is stored under `GRPO/`. |
|
|
| ## Download |
|
|
| ```bash |
| hf download youqiwong/ForgeryVCR \ |
| --repo-type model \ |
| --include "GRPO/*" \ |
| --local-dir weights/ForgeryVCR |
| ``` |
|
|
| Use the checkpoint from the |
| [ForgeryVCR repository](https://github.com/youqiwong/ForgeryVCR): |
|
|
| ```bash |
| INFERENCE_MODEL_PATH=weights/ForgeryVCR/GRPO \ |
| INFERENCE_DATASETS="all" \ |
| bash scripts/run_inference.sh |
| ``` |
|
|
| The full tool definitions, prompts, preprocessing, SAM2 mask generation, and |
| evaluation code are maintained in the project repository. |
|
|
