Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/afondiel/prompt-engineering-for-vision-models-deeplearningai

These notes and resources are compiled from the crash course Prompt Engineering for Vision Models offered by DeepLearning.AI.
https://github.com/afondiel/prompt-engineering-for-vision-models-deeplearningai

cnn convnets diffusion-models image-processing large-vision-language-models large-vision-models meta-sam prompt-engineering video-processing vision-language-model vision-model-prompting vision-models visual-prompting vit

Last synced: 9 days ago
JSON representation

These notes and resources are compiled from the crash course Prompt Engineering for Vision Models offered by DeepLearning.AI.

Host: GitHub
URL: https://github.com/afondiel/prompt-engineering-for-vision-models-deeplearningai
Owner: afondiel
Created: 2024-07-04T18:13:11.000Z (6 months ago)
Default Branch: main
Last Pushed: 2024-08-20T15:41:00.000Z (5 months ago)
Last Synced: 2024-11-06T05:15:08.874Z (about 2 months ago)
Topics: cnn, convnets, diffusion-models, image-processing, large-vision-language-models, large-vision-models, meta-sam, prompt-engineering, video-processing, vision-language-model, vision-model-prompting, vision-models, visual-prompting, vit
Language: Jupyter Notebook
Homepage: https://learn.deeplearning.ai/courses/prompt-engineering-for-vision-models/lesson/1/introduction
Size: 103 MB
Stars: 1
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

        # Prompt Engineering for Vision Models (DeepLearning.AI)



(Source: [SAM](https://github.com/facebookresearch/segment-anything))

## Overview

These notes and resources are compiled from the crash course [Prompt Engineering for Vision Models](https://learn.deeplearning.ai/courses/prompt-engineering-for-vision-models/lesson/1/introduction) like [Meta's SAM (Segment Anything Model)](https://segment-anything.com/) or [Stable Diffusion](https://huggingface.co/stabilityai/stable-diffusion-3-medium), offered by [DeepLearning.AI](https://www.deeplearning.ai/).

The course, led by `Andrew Ng` and instructors from [Comet](https://www.comet.com/site/) (**Abby Morgan, Jacques Verré, and Caleb Kaiser**), explores techniques for prompting vision models like image generation and object detection.

## Key Concepts

- Gain a foundational understanding of prompt engineering techniques for guiding vision models.

- Explore methods for image generation, object detection, and image segmentation using text prompts.

- Learn to fine-tune diffusion models for personalized image creation with DreamBooth.

- Discover best practices for experimenting and tracking progress in prompt engineering workflows.

## Course Contents

- [Lesson0: Introduction](./L0_introduction_notes.md)

- [Lesson1: Overview](./L1_overview_notes.md)

- [Lesson2: Image Segmentation](./L2_image_segmentation_notes.md)

- [Lesson3: Object Detection](./L3_object_detection_notes.md)

- [Lesson4: Image Generation](./L4_image_generation_notes.md)

- [Lesson5: Fine-tuning](./L5_fine_tuning_notes.md)

- [Lesson6: Conclusion](./L6_conclusion-notes.md)

## Setup & Requirements  

**Requirements**

- All you need is a [Deep LearningAI](https://learn.deeplearning.ai/courses/prompt-engineering-for-vision-models/lesson/1/introduction) user account to start learning for free.

## Lab: Hands-on Exercises 

|Chapter|Notebook|

|--|--|

|[Lesson0: Introduction](#)| -|

|[Lesson1: Overview](#)|-|

|[Lesson2: Image Segmentation](#)|[![Open notebook in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/afondiel/Prompt-Engineering-for-Vision-Models-DeepLearningAI/blob/main/lab/notebooks/L2/L2_Image_Segmentation.ipynb)|

|[Lesson3: Object Detection](#)|[![Open notebook in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/afondiel/Prompt-Engineering-for-Vision-Models-DeepLearningAI/blob/main/lab/notebooks/L3/L3_Object_Detection.ipynb)|

|[Lesson4: Image Generation](#)|[![Open notebook in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/afondiel/Prompt-Engineering-for-Vision-Models-DeepLearningAI/blob/main/lab/notebooks/L4/L4_Image_Generation.ipynb)|

|[Lesson5: Fine-tuning](#)|[![Open notebook in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/afondiel/Prompt-Engineering-for-Vision-Models-DeepLearningAI/blob/main/lab/notebooks/L5/L5_Fine_Tuning.ipynb)|

## References

Main Course : 

- https://learn.deeplearning.ai/courses/prompt-engineering-for-vision-models/lesson/1/introduction

Others short Free Courses available on DeepLearning.AI : 

- https://learn.deeplearning.ai/

Resources:

- [Awesome-Diffusion-Models: A collection of resources and papers on Diffusion Models](https://github.com/diff-usion/Awesome-Diffusion-Models)