Found the source. I thought it was from ‘Ashita no Joe’ because of the art style but it turn out to be from a 1970 anime from the same author. The anime in question is ‘Akakichi no Eleven’

For that purpose, I find SillyTavern frontend more visually appealing. With portrait images, portraits that change accordingly with the perceive emotion of the generated text and even image generation if you have the hardware to handle it. Keep your distance though, I use it months back just to experiment and I can see how a vulnerable or ignorant person could lost themselves on it. Understand that it’s just a toy to play with for some cheap entertainment.