USER: You need to generate an input prompt for a text-to-image neural network. The system accepts as correct the query string, where all arguments are separated by commas. The words in prompt are crucial. Users need to prompt what they want to see, specifying artist names, media sources, or art styles to get desired results. Be descriptive in a manne similar to prompts provided below about what you want. It is more sensitive to precise wording. That includes adjectives and prepositions like "in front of [object]", and "taken by [camera name]". It also supports weights. By bracketing the words you can change their importance. For example, (rainy) would be twice as important compared to "rainy" for the model, and [rainy] would be half as important. Write a medium lenth prompt, like below. Too long and it would fail to generate, too short and it would generate crap. Be as detailed as possible and avoid both scenarios at any cost. As photographers and painters know, light has a huge effect on the final impression an image creates. Specify lighting conditions. Describe the type of light you want to see and the time of day it is. You don't need complex vocabulary. The MOST IMPORTANT thing is that a text-to-image neural network interprets the prompt from up to down, i.e. what is listed at the beginning of the prompt is more significant than what is listed near the end of the prompt. So it is recommended to place the subject of prompt in the beginning, characteristical tags in the middle a...

USER: The elves are walking along a forest trail, with mountains in the distance. They are carrying backpacks, bows, swords, and other equipment. They look happy and interested. Alaric walks ahead, he looks serious and determined. He holds in his hand a map marking the ruins of Arcanum. Frame description: The shot is taken from a bird's eye view. We see the elves from behind as they move along the trail. We see the forest around them, which looks green and alive. We see mountains on the horizon that look blue and misty. We see the sky above them, which looks blue and clear. Frame construction: The frame has a horizontal composition. The elves occupy the center of the frame, and the forest, mountains, and sky provide the background for them. The frame has a balance between dynamics and statics. Dynamics is created by the movement of the elves on the path, while statics is created by the shapes of the forest, mountains and sky. Frame light: The frame has natural light. The light comes from the sun, which is to the left of the frame. The light illuminates the elves from the side, creating a contrast between the light and dark side of their bodies and clothing. The light also reflects off the leaves of the forest, creating green highlights on the elves. Light also shines through the mist of the mountains, creating blue shadows on them. Main colors of the frame: The frame has a cold color scheme. The main colors of the frame are green, blue, and white. Green is associated with the fores...

USER: You need to generate an input prompt for a text-to-image neural network. The system accepts as correct the query string, where all arguments are separated by commas. The words in prompt are crucial. Users need to prompt what they want to see, specifying artist names, media sources, or art styles to get desired results. Be descriptive in a manne similar to prompts provided below about what you want. It is more sensitive to precise wording. That includes adjectives and prepositions like "in front of [object]", and "taken by [camera name]". It also supports weights. By bracketing the words you can change their importance. For example, (rainy) would be twice as important compared to "rainy" for the model, and [rainy] would be half as important. Write a medium lenth prompt, like below. Too long and it would fail to generate, too short and it would generate crap. Be as detailed as possible and avoid both scenarios at any cost. As photographers and painters know, light has a huge effect on the final impression an image creates. Specify lighting conditions. Describe the type of light you want to see and the time of day it is. You don't need complex vocabulary. The MOST IMPORTANT thing is that a text-to-image neural network interprets the prompt from up to down, i.e. what is listed at the beginning of the prompt is more significant than what is listed near the end of the prompt. So it is recommended to place the subject of prompt in the beginning, characteristical tags in the middle a...

USER: The elves enter the ruins of Arcanum. They see huge walls, towers, arches, and statues of gray stone. They look delighted and frightened. Alaric leads them to the center of the ruins, where a large black portal can be seen. He looks determined and ambitious. He says, "This is it, this is what I've been looking for. Soon everything will be mine!" Frame description: The shot is taken from a high angle. We see the elves from below as they move through the ruins. We see the ruins around them, which look gray and dead. We see the portal in the center of the ruins, which looks black and ominous. We see the sky above them, which looks dark and cloudy. Frame construction: The frame has a vertical composition. The elves occupy the bottom part of the frame, while the ruins, the portal and the sky create the background for them. The frame has a dynamic character. The dynamics is created by the movement of the elves through the ruins, and the contrast between the portal and the sky. The frame also has a focus on Alaric, who stands out for his position and action. Frame Light: The frame has natural light. The light comes from the sun, which is on the right side of the frame. The light illuminates the elves from the side, creating a contrast between the light and dark side of their bodies and clothing. The light also emphasizes the details of the ruins and the portal. The light also creates shadows on the ground and sky. Main colors of the frame: The frame has a cold color scheme. The main...

USER: You need to generate an input prompt for a text-to-image neural network. The system accepts as correct the query string, where all arguments are separated by commas. The words in prompt are crucial. Users need to prompt what they want to see, specifying artist names, media sources, or art styles to get desired results. Be descriptive in a manne similar to prompts provided below about what you want. It is more sensitive to precise wording. That includes adjectives and prepositions like "in front of [object]", and "taken by [camera name]". It also supports weights. By bracketing the words you can change their importance. For example, (rainy) would be twice as important compared to "rainy" for the model, and [rainy] would be half as important. Write a medium lenth prompt, like below. Too long and it would fail to generate, too short and it would generate crap. Be as detailed as possible and avoid both scenarios at any cost. As photographers and painters know, light has a huge effect on the final impression an image creates. Specify lighting conditions. Describe the type of light you want to see and the time of day it is. You don't need complex vocabulary. The MOST IMPORTANT thing is that a text-to-image neural network interprets the prompt from up to down, i.e. what is listed at the beginning of the prompt is more significant than what is listed near the end of the prompt. So it is recommended to place the subject of prompt in the beginning, characteristical tags in the middle a...

USER: The Sword of Destiny unleashes a powerful blast of darkness that destroys the ruins and everything around it. The abyss instantly consumes the elves. The explosion also creates a portal that connects this world to another world: the world of demons. Thousands of demons emerge from the portal: horrible creatures of flesh and fire. They begin their invasion of this world. Alaric sees this and realizes his mistake. He looks horrified and remorseful. He says, "What have I done? I am damned!" Frame description: The shot is taken from a long distance. We see the ruins and the portal in the center of the frame, which look black and ominous. We see an explosion of darkness that looks purple and destructive. We see an abyss that looks blue and consuming. We see demons that look red and violent. We see Alaric in the lower left corner of the frame as he stands on the edge of the abyss. We see his face, which expresses fear and remorse. Frame construction: The frame has a horizontal composition. The ruins and the portal occupy the center of the frame, while the explosion of darkness, the abyss and the demons create the background for them. The frame has a dynamic character. Dynamics are created by the movement of the explosion of darkness, the abyss and the demons, as well as the contrast between them. The frame also has a focus on Alaric, who stands out for his position and action. Frame Light: The frame has artificial light. The light comes from the blast of darkness, the portal and th...