| | --- |
| | library_name: diffusers |
| | --- |
| | |
| | # Florence-2 Image Annotator |
| |
|
| | A custom [Modular Diffusers](https://huggingface.co/docs/diffusers/modular_diffusers/overview) block that uses [Florence-2](https://huggingface.co/docs/transformers/model_doc/florence2) for image annotation tasks like segmentation, object detection, and captioning. |
| |
|
| | ## How to use |
| |
|
| |
|
| | ```python |
| | import torch |
| | from diffusers import ModularPipeline |
| | from diffusers.utils import load_image |
| | |
| | # Load the block |
| | image_annotator = ModularPipeline.from_pretrained( |
| | "diffusers/Florence2-image-Annotator", |
| | trust_remote_code=True |
| | ) |
| | image_annotator.load_components(torch_dtype=torch.bfloat16) |
| | image_annotator.to("cuda") |
| | |
| | # Load an image |
| | image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg") |
| | image = image.resize((1024, 1024)) |
| | |
| | # Generate a segmentation mask |
| | output = image_annotator( |
| | image=image, |
| | annotation_task="<REFERRING_EXPRESSION_SEGMENTATION>", |
| | annotation_prompt="the car", |
| | annotation_output_type="mask_image", |
| | ).images[0] |
| | output.save("car-mask.png") |
| | ``` |
| |
|
| | ### Compose with Inpainting Pipeline |
| |
|
| | ```python |
| | from diffusers import ModularPipeline |
| | |
| | # Load the annotator |
| | image_annotator = ModularPipeline.from_pretrained( |
| | "diffusers/Florence2-image-Annotator", |
| | trust_remote_code=True |
| | ) |
| | |
| | # Get an inpainting workflow and insert the annotator |
| | # repo_id = .. # you can use SDXL/flux/qwen any pipeline support Inpaint |
| | inpaint_blocks = ModularPipeline.from_pretrained(repo_id).blocks.get_workflow("inpainting") |
| | inpaint_blocks.sub_blocks.insert("image_annotator", image_annotator.blocks, 0) |
| | |
| | # Initialize the combined pipeline |
| | pipe = inpaint_blocks.init_pipeline() |
| | pipe.load_components(torch_dtype=torch.float16, device="cuda") |
| | |
| | # Inpaint with automatic mask generation |
| | output = pipe( |
| | prompt=prompt, |
| | image=image, |
| | annotation_task="<REFERRING_EXPRESSION_SEGMENTATION>", |
| | annotation_prompt="the car", |
| | annotation_output_type="mask_image", |
| | num_inference_steps=30, |
| | ).images[0] |
| | output.save("inpainted-car.png") |
| | ``` |
| |
|
| | ## Supported Tasks |
| |
|
| | | Task | Description | |
| | |------|-------------| |
| | | `<OD>` | Object detection | |
| | | `<REFERRING_EXPRESSION_SEGMENTATION>` | Segment specific objects based on text | |
| | | `<CAPTION>` | Generate image caption | |
| | | `<DETAILED_CAPTION>` | Generate detailed caption | |
| | | `<MORE_DETAILED_CAPTION>` | Generate very detailed caption | |
| | | `<DENSE_REGION_CAPTION>` | Caption different regions | |
| | | `<CAPTION_TO_PHRASE_GROUNDING>` | Ground phrases to regions | |
| | | `<OPEN_VOCABULARY_DETECTION>` | Detect objects from open vocabulary | |
| |
|
| | ## Output Types |
| |
|
| | | Type | Description | |
| | |------|-------------| |
| | | `mask_image` | Black and white mask image | |
| | | `mask_overlay` | Mask overlaid on original image | |
| | | `bounding_box` | Bounding boxes drawn on image | |
| |
|
| | ## Inputs |
| |
|
| | | Parameter | Type | Required | Default | Description | |
| | |-----------|------|----------|---------|-------------| |
| | | `image` | `PIL.Image` | Yes | - | Image to annotate | |
| | | `annotation_task` | `str` | No | `<REFERRING_EXPRESSION_SEGMENTATION>` | Task to perform | |
| | | `annotation_prompt` | `str` | Yes | - | Text prompt for the task | |
| | | `annotation_output_type` | `str` | No | `mask_image` | Output format | |
| |
|
| | ## Outputs |
| |
|
| | | Parameter | Type | Description | |
| | |-----------|------|-------------| |
| | | `mask_image` | `PIL.Image` | Generated mask (when output type is `mask_image`) | |
| | | `image` | `PIL.Image` | Annotated image (when output type is `mask_overlay` or `bounding_box`) | |
| | | `annotations` | `dict` | Raw annotation predictions | |
| |
|
| | ## Components |
| |
|
| | This block uses the following models from [florence-community/Florence-2-base-ft](https://huggingface.co/florence-community/Florence-2-base-ft): |
| |
|
| | - `image_annotator`: `Florence2ForConditionalGeneration` |
| | - `image_annotator_processor`: `AutoProcessor` |
| |
|
| | ## Learn More |
| |
|
| | - [Building Custom Blocks Guide](https://huggingface.co/docs/diffusers/modular_diffusers/custom_blocks) |
| | - [Modular Diffusers Overview](https://huggingface.co/docs/diffusers/modular_diffusers/overview) |
| | - [Modular Diffusers Custom Blocks Collection](https://huggingface.co/collections/diffusers/modular-diffusers-custom-blocks) |
