Low-poly render of X high resolution, 4k.Other DALL-E/craiyon prompt templates for future use: You can then also add a style cue like ‘Ghibli inspired’, ‘Giger’ or ‘Salvador Dali’. ‘Cluttered house in the woods | anime oil painting high resolution cottagecore ghibli inspired 4k’Īs you can see, just appending ”| oil painting high resolution 4k” will improve most of your results.
Fantasy page art text how to#
If you have any tips on how to do better, tell me on Twitter.įor example, this is a prompt that gave me great results in Craiyon. Using this simple framework often gets me results close to what I want. Then I append “style clues” like “anime/Picasso/Giger -always good results-/Junji Ito”.“Gorgeous/amazing/beautiful” + “digital painting/oil painting/digital art/canvas/3d render” + any of “unreal engine/unity engine”.Usually, what I do is write what I want (adjectives + nouns usually get better results than verbs or complex scenes), then append How to write prompts for DALL-E / StableDiffusion I also wrote separate articles after experimenting with OpenAI’s DALL-E 2 and its open source competition, StableDiffusion both of which blew my mind and made me think of the future differently.
Fantasy page art text free#
It’s free and open source, and I’m loving it. Update: Besides Craiyon, I’ve found Dall-E Flow, a colab notebook that uses Jina-AI to be the best tool for generating beautiful DALL-E images, and I recommend everyone to give it a spin. I mostly tried prompts that dealt with Biblical or mythological themes, because for some reason I found most people didn’t do those sorts of prompts as much (or maybe because I’m a big fantasy/D&D geek). Bigger models usually deal better with humanoid or animal shapes, and construct scenes better when they include action.įeel free to steal any of these images and use them for anything, or share them on social media. However, illustrations containing animals, people, humanoids or anything that moves, or prompts that ask for a specific action or use verbs, usually get poor results. My general idea is that DALL-E mini can generate satisfying results when the prompt is well-constructed enough, if asked to generate images of inanimate objects, landscapes, buildings and so on. I also hope seeing these prompts can give you a small hint of how to make better prompts for your own ideas (usually, just appending ‘digital painting’ or ‘oil painting’ and ‘artstation’ in the end will do half of the trick). I found the comparisons where I used the same prompt in both models to be particularly interesting in showcasing how much better DALL-E mini is at composition, even though VQVAE, being bigger and taking longer, generates images at a higher resolution and thus renders textures and objects in a more believable way. The first batch is all made with EleutherAI’s imagine model, and the second one was made with DALL-E Mini, which can be told from the screenshot’s visible UI. These were cherrypicked, as they were the ones I liked the most. Then a showcase of the prompts I used for generating images, and the images I obtained. What follow are a small guide on prompt engineering for dall-e mini and other text-to-image models. imagine model (which I think is a VQVAE like DALL-E) and some I made using everyone’s favorite viral text-to-image generator, DALL-E Mini (a small open source version of DALL-E 2, a guided diffusion model with extra steps). Here are some of the images I made with EleutherAI’s. Giving a model a prompt to generate an image out-of becomes sort of addictive, and I’ve spent longer than I am proud to admit fiddling around with these. I think interpretability is a fascinating field of study, and understanding a model’s representations may yield ideas for better models in the future (though usually the simplest way to make a better model is training a bigger one with more compute). The idea of text-to-image generators like CLIP or GLIDE is even more astounding, and I love being able to play with them and trying to get a glimpse of the way they “perceive” textual and image inputs. But what I was interested in was how could I write better prompts that yielded the most beautiful images? Text to Image Art: Experiments and Prompt Guide for DALL-E Mini and Other AI Art ModelsĮver since DALL-E came out in January 2021, or even before that with PixelRNN, I’ve found generative models, especially for images, amazing.
0 kommentar(er)
