High performance materials are a key tool for the improvement of several fields such as aeronautics, construction or biotechnology and also to allow more efficient use of energy in industrial processes where that use becomes intensive with its consequences in terms of environmental and economic sustainability. For these reasons, the emergence of high-performance materials such as high entropy alloys (HEAs) has captured the attention of industry and researchers within the last years. However, the development of these materials requires a large amount of time and money invested in the design, synthesizability evaluation, construction and characterization of such compounds. The use of artificial intelligence for the design, even in its current infancy status, provides a valuable tool to accelerate the initial phases of materials design and HEAs. In this work, a Generative based approach is used, namely Generative Adversarial Networks (GANs) to generate synthetic HEAs for highly intensive industrial processes. The architecture model of a GAN involves two neural networks. The fist one is a generator model for generating chemical compositions of candidate alloys to form the HEAs. The second one is a discriminator model for classifying the generated samples coming from the generator in real or fake compositions. The discriminator learns from a specific data structure that contains data from real samples to classify the generated samples. A GAN extension that conditionally generates the synthetic outputs by the addition of extra inputs was used. This so-called conditional tabular generative adversarial network (CTGAN) was developed to be used with tabular datasets as input. Such data is normally composed of a mix of continuous and discrete columns, making some deep neural network models fail in performing a properly modeling for this kind of inputs. In the present approach, the generated realistic synthetic data was based on the conventional parametric design parameters used for HEAs. As conditioned input data, the chemical composition of the alloys and their phase was classified in four classes, namely amorphous, intermetallic, solid solution and solid solution+intermetallic, which can be used as an indicator for their applicability. The CTGAN provides as output candidates of HEAs, the expected parameters mentioned above and corresponding phase. The generated data is compared with the calculated data and a verification of novel generated compositions is done in open materials databases based on DFT. A specific data structure for the CTGAN training and results of the performance of this approach is provided, which was developed in the framework of the European project ACHIEF for the discovery of novel materials to be used in industrial processes. Here, it is concluded that CTGAN suits the purpose of generating new kind of these materials using DFT as a proper method for validation. As for next steps, in order to enhance Artificial Intelligence potential for Material Science we propose the implementation of a reinforcement learning framework for the screening of the compounds according to the desired properties while being generated.