الصفحة 1
الصفحة 1
Generative adversarial text to image synthesis
Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing text-to-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In order to make the project more specialized, it was approved that the project be dedicated to fashion image generation, we present an effective approach for generating new clothing through generative adversarial learning. Generative Adversarial Networks (GANs) successfully show the capability of synthesizing sharper images compared to other generative models.
Fashionity
This project is an AI fashion design system to generate fashion images based on user textual description. The proposed system incorporates advanced technology for dissemination and machine translation with the aim of facilitating a seamless user experience for input in both Arabic and English languages. Moreover, the project encompasses the incorporation of a recommendation system that proposes appropriate visual content based on user style. The primary objective of this project is to develop a robust framework capable of generating high-quality images based on textual descriptions, providing recommendations for similar clothing items, and facilitating the retrieval of photographic and apparel articles through image search.
Cartoony story app = تطبيق قصة كارتونية
The translation of textual narratives into immersive visual representations poses a significant challenge in the field of artificial intelligence. Traditional cartoon generation techniques face formidable technical challenges and require substantial resources. Research efforts towards direct video synthesis from text have encountered obstacles in developing efficient techniques. In parallel, researchers propose an alternative approach involving the generation of dynamic sequences of images portraying children's story narratives. This approach includes applying various visual effects to highlight motion, interaction, and excitement in storytelling. By dynamically generating a sequence of images reflecting the narrative's progression and applying diverse visual effects, this alternative method offers a flexible and practical solution to cartoon generation challenges, providing an efficient and effective experience akin to video while retaining the magical appeal of visual storytelling. ...
