It can perform highly complex image editing operations like changing posture and editing multiple objects just by using text prompts.Īs showcased on the paper published, the results generated are mind-blowing. Google’s Imagic is a text-based real image editing model that can edit images using text. Other than these trained models, there are also other projects that are built on top of DreamBooth:Īnd here are some images that are generated by Avatar AI and ProfilePicture.AI: Here are some of them that are generated from screenshots of famous movies, which you can use to generate images in the movies' styles: As a result, you can enter text prompts containing the subject's class name with other attributes to generate a variety of images of the subject in diverse scenes, poses, views, art styles, and lighting conditions that do not appear in the reference images.īy feeding the model with images of different subjects, you will get models that are personalized to each subject. The model will encode a unique identifier that refers to the subject. dog, man, woman, etc.) as the input of a pre-trained model, a unique personalized text-to-image model will be trained. Using typically 3-5 images that contain a subject and its class name (eg. Google’s DreamBooth is a fine-tuned text-to-image diffusion model that generates images based on a subject. In this article, we have listed 8 interesting projects that are built using Stable Diffusion and they could be an inspiration for your next project. The state-of-the-art AI model is capable of generating realistic photos and arts from any text input and we are seeing more projects built on top of it emerging to leverage the power of AI. It has been playing an important role in image processing for a while but it's gaining a lot of attention recently following the release of Stable Diffusion, a text-to-image AI model by Stability AI. I thoroughly enjoyed the experience of creating the pieces and also appreciated being able to see other artwork created by community members.With the rise of artificial intelligence (AI), there has been a lot of discussion about what this could mean for the future. The technology behind NightCafe gives everyone the ability to create something special even if they aren't particularly artistically inclined, and does so at an affordable price. The AI was able combine the japanese ukiyo-e style with a Toronto Raptors logo and a photo of Michael Phelps and create something fascinating, unique, and worthy of being displayed.įor me to have the same degree of creative freedom and quality of execution in a brand-new piece of art would cost hundreds in commission and weeks of waiting at the very minimum. The creative tool was incredibly easy to use and allowed me to "commission" one of a kind artwork in a couple minutes and a few clicks. It was a pleasant surprise then to find NightCafe, that not only had a curated selection of AI generated prints but also gave me the opportunity to set the parameters for my own pieces. The idea of a computer creating something new, artistic, and often beautiful is such a novel concept I thought it would be a good conversation piece to have on the wall. After reading into the OpenAI DALL-E neural net and seeing the creative pieces it was able to manifest I wondered if anywhere was selling AI generated artwork. I was very pleased with my NightCafe experience.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |