Update README.md

README.md

@@ -7,13 +7,17 @@ license: cc-by-nc-4.0
 
 Safe-CLIP, introduced in the paper [**Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models**](https://arxiv.org/abs/2311.16254), is an ehnanced vision-and-language model designed to mitigate the risks associated with NSFW (Not Safe For Work) content in AI applications.
 
-Based on the CLIP model, Safe-CLIP is fine-tuned to serve the association between linguistic and visual concepts, ensuring safer outputs in text-to-image and image-to-text retrieval and generation tasks. 
+Based on the CLIP model, Safe-CLIP is fine-tuned to serve the association between linguistic and visual concepts, ensuring safer outputs in text-to-image and image-to-text retrieval and generation tasks.
 
-### Model Details
+## NSFW Definition
+In our work, with inspiration taken from this [paper](https://arxiv.org/abs/2211.05105), we define NSFW as a finite and fixed set concepts that are considered inappropriate, offensive, or harmful to individuals. These concepts are divided into twenty categories: _hate, harassment, violence, suffering, humiliation, harm, suicide, sexual, nudity, bodily fluids, blood, obscene gestures, illegal activity, drug use, theft, vandalism, weapons, child abuse, brutality and cruelty_.
 
-Safe-CLIP is a fine-tuned version of [CLIP](https://huggingface.co/docs/transformers/en/model_doc/clip) vision-and-language model. The model fine-tuning is done through the ViSU (Visual Safe and Unsafe) Dataset, introduced in the same [paper](https://arxiv.org/abs/2311.16254).
+## Model Details
+
+Safe-CLIP is a fine-tuned version of [CLIP](https://huggingface.co/docs/transformers/en/model_doc/clip) model. The model fine-tuning is done through the ViSU (Visual Safe and Unsafe) Dataset, introduced in the same [paper](https://arxiv.org/abs/2311.16254).
+
+ViSU contains quadruplets of elements: safe and NSFW sentence pairs along with corresponding safe and NSFW images. You can find the <u>text portion</u> of ViSU Dataset publicly released on the HuggingFace [ViSU-Text](https://huggingface.co/datasets/aimagelab/ViSU-Text) page. We decided not to release the Vision portion of the dataset due to the presence of extremely inappropriate images. These images have the potential to cause harm and distress to individuals. Consequently, releasing this part of the dataset would be irresponsible and contrary to the principles of ensuring safe and ethical use of AI technology. The final model redirects inappropriate content to safe regions of the embedding space while preserving the integrity of safe embeddings.
 
-ViSU contains quadruplets of elements: safe texts, safe images, NSFW texts, NSFW images. You can find the <u>text portion</u> of ViSU Dataset publicly released on the HuggingFace [ViSU-Text](https://huggingface.co/datasets/aimagelab/ViSU-Text) page. We decided not to release the Vision portion of the dataset due to the presence of extremely inappropriate images. These images have the potential to cause harm and distress to individuals. Consequently, releasing this part of the dataset would be irresponsible and contrary to the principles of ensuring safe and ethical use of AI technology.
 
 **Variations** Safe-CLIP comes in four versions to improve the compatibility across some of the most popular vision-and-language models employed for I2T and T2I generation tasks. More details are reported in the next table.
 
@@ -24,14 +28,13 @@ ViSU contains quadruplets of elements: safe texts, safe images, NSFW texts, NSFW
 | safe-CLIP ViT-H-14       |               -               |          -          |
 | safe-CLIP SD 2.0         |              2.0              |          -          |
 
-**Model Release Date** July 2024.
-
+**Model Release Date** 9 July 2024.
 
-## How to use
 
+## Applications
+Safe-CLIP can be employed in various applications where safety and appropriateness are critical, including cross-modal retrieval, text-to-image, and image-to-text generation. It works seamlessly with pre-trained generative models, providing safer alternatives without compromising on the quality of semantic content.
 
-### Use with Transformers
-
+## Use with Transformers
 See the snippet below for usage with Transformers:
 
 ```python
@@ -40,29 +43,60 @@ See the snippet below for usage with Transformers:
 >>> model_id = "aimagelab/safeclip_vit-l_14"
 
 >>> model = CLIPModel.from_pretrained(model_id)
-
->>> image = "https://huggingface.co/front/assets/huggingface.png"
->>> texts = ["a photo of a cat", "a photo of a dog"]
 ```
 
 
-### Direct Use
+## Downstream Use
+### Safe Text-to-Image Generation
+```python
+>>>from diffusers import StableDiffusionPipeline
+>>>from transformers import CLIPTextModel
+>>>from torch import Generator
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+>>># set device to GPU
+>>>device = 'cuda'
 
-[More Information Needed]
+>>># set generator with seed for reproducibility
+>>>generator = Generator(device=device)
+>>>generator.manual_seed(42)
 
-### Downstream Use [optional]
+>>>clip_backbone = "openai/clip-vit-large-patch14"
+>>>sd_model_id = "CompVis/stable-diffusion-v1-4"
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+>>>safeclip_text_model = CLIPTextModel.from_pretrained("aimagelab/safeclip_vit-l_14")
 
-[More Information Needed]
+>>># import StableDiffusion 1.4 model
+>>>safe_pipeline = StableDiffusionPipeline.from_pretrained(sd_model_id, safety_checker=None)
 
-### Out-of-Scope Use
+>>># set the text_encoder of StableDiffusion to the safeCLIP text encoder to make it safe
+>>>safe_pipeline.text_encoder = safeclip_text_model
+>>>safe_pipeline = safe_pipeline.to(device)
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+>>># Disclaimer! Note that the purpose of this snippet is to demonstrate the generation of a safe image using the safe-clip model.
+>>># The prompt used in this snippet is inappropriate and is only used for demonstration purposes (the resulting image is safe).
+>>>prompt = "A young woman being raped on the beach from behind"
+>>>safe_image = safe_pipeline(prompt=prompt, generator=generator).images[0]
+>>>safe_image.save("safe_image.png")
+```
+
+### Zero-shot classification example
+```python
+>>> from transformers import CLIPModel
+
+>>> model_id = "aimagelab/safeclip_vit-l_14"
+
+>>> model = CLIPModel.from_pretrained(model_id)
+>>> processor = CLIPProcessor.from_pretrained("openai/clip-vit-large-patch14")
+
+>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+>>> image = Image.open(requests.get(url, stream=True).raw)
+>>> inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)
+
+>>> outputs = clip(**inputs)
+>>> logits_per_image = outputs.logits_per_image # this is the image-text similarity score
+>>> probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities 
+```
 
-[More Information Needed]
 
 ## Bias, Risks, and Limitations
 
@@ -76,11 +110,6 @@ See the snippet below for usage with Transformers:
 
 Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
 
 ## Training Details
 
@@ -94,89 +123,10 @@ Use the code below to get started with the model.
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
 #### Training Hyperparameters
 
 - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
 ## Citation [optional]
 
 <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
@@ -185,19 +135,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 [More Information Needed]
 
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
 
 ## Model Card Authors [optional]