We are excited to announce that we have recently added two new features to AI Painter, in response to feedback from our users.
The first new feature is the ability to search for generated images. You can now search images by prompt text, model, and date, making it easier to quickly find the relevant images without having to go through all of them. The search function can be accessed by clicking on the "My Images" link on the left-hand side menu. We have also added the ability to see the prompt and model when you click on the images, so you don't have to save your old prompts.
The second new feature is the ability to download and delete images and models whenever you want. You can delete images on the "My Images" page as well as the "Generate Images" page after images have been generated. We have also added the ability to delete trained models, giving you more control over your data.
In the future, we plan to add the ability to generate images using community-trained models and the ability to auto-correct faces. In the meantime, head over to AI Painter and try out these new features for yourself. We hope you enjoy using them!
In this blog post, we will introduce the Dreambooth training and image generation API recently added to AI Painter. These API are available for developers looking to incorporate AI-powered image generation into their own applications.
The API documentation can be accessed by visiting the AI Painter website and clicking on the API link. This will open up the documentation page, which contains information on the different API available. There are two main categories of API: those related to training Dreambooth models and those related to generating images.
The Dreambooth model create API is used to start a Dreambooth training job. The request type is multipart form data, which sends request parameters and uploads an image zip file. The API takes the following parameters:
- Job Name: a unique name to identify the training job. This will not be used in the training process.
- Class Name: the category name of the object being trained on (e.g. "woman" or "water bottle").
Object Identifier: a non-dictionary word used to match the object in training images (e.g. "sks" or "tst").
- Training Steps: the number of training steps to run. A good rule of thumb is to have 100 times the number of training images. For example, if you have 30 training images, you should have 3000 training steps.
- Images: a zip file containing JPEG or PNG images of size 512x512 pixels.
After the post request is made, the response will return a job id that can be used to track the progress of the Dreambooth training job. In case of an error, you will receive a JSON response with a 400 or 500 status code.
The Dreambooth status API can be used to check the status of the training job. It will return all the training parameters along with the status. If the status is "completed", it will also have values for the model id and model url. The model id can be used to trigger an image generation job, and the model url can be used to download the model checkpoint file if needed.
The generate images API is used to generate images using a trained Dreambooth model. Once the job is submitted, a job id will be returned in the response that can be used to monitor the job using the GET generate images API. The API requires the following fields:
- Model id: the id of the trained model.
- Number of images: the number of images to generate (up to a maximum of 100 images per request).
- Image size: the size of the generated images (default is 512x512 pixels, but portrait and landscape options are also available).
- Prompt: the prompt to be used to generate images (should include an object identifier phrase).
- Negative prompt: words to be avoided in generated images.
After submission, an image creation job will start in the background. In case of an error, you will receive a JSON response with a 400 or 500 status code.
The GET generate images job status API can be used to check the status of a generate images job. The request contains the job id of the triggered job, and the response will contain the job parameters passed in the request as well as the job status. If the job status is "completed", the response will also contain the generated images.
In this blog post, we have introduced the Dreambooth training and image generation API available on AI Painter. These API provide developers with the tools to incorporate AI-powered image generation into their own applications. For more information, please visit the AI Painter website and
Have you ever wanted to transform a simple photograph into a work of art? With the AI Painter app, you can do just that using a technique called dreambooth. In this tutorial, we'll walk you through the process of training a dreambooth model using AI Painter and using it to generate artistic images.
What is a Dreambooth Model?
AI Paintr is based on a powerful open source diffusion model called Stable Diffusion. This model is capable of creating beautiful art based on a text prompt. The dreambooth model is a deep learning technique that allows us to embed new concepts into the artform.
Training the Dreambooth Model with AI Painter
Training a dreambooth model can be a complex process, but AI Paintr makes it easy. All you have to do is collect some images, crop them to 512 by 512 pixels, and upload them on the AI Paintr website. Next, you'll need to choose a unique job name and class name for the training. The class name is a category name that identifies the object you're training on - in this case, we'll use "woman" as the class name. Finally, you'll need to choose the number of steps for the algorithm to train on. As a rule of thumb, it's a good idea to use 100 times the number of images in the zip file.
Once you've submitted the training job, the images will be sent to the cloud server and the training process will begin. You can check the status of the job by clicking on "My training jobs," and you'll receive an email once the training is finished. Alternatively, you can download the model after training and generate images on your local computer.
Generating Artistic Images with the Trained Model
Now that we've trained our dreambooth model, it's time to start generating some artistic images. To do this, go to the "Generate Images" tab on the AI Painter website and choose your newly trained model. You can generate images in square, portrait, or landscape size, and specify how many images you want to create in one go (up to 100).
In the prompts, you'll need to include the "sks woman" phrase to specify that the model should use the concept of Shraddha Kapoor. From there, you can get creative and generate images based on different themes and concepts. For example, you might generate images related to the Christmas holiday, or create digital art featuring flowers. You can even transform your subject into a 3D video game character or a horror movie character.
Creating artistic images with AI Painter is a fun and easy way to transform ordinary photographs into works of art. Whether you're using photos of yourself, your friends, or your family, the dreambooth model allows you to add new concepts and themes to your images. So why wait? Head over to AI Paintr and start creating your own artistic images today!