You heard the buzz: there’s another way to do art. You type a few text prompts, and the AI will return results. One of the recent AI generative art lab is Midjourney. You can try it for free on MidJourney’s Discord server with a limited number of images.
Here are some of my attempts:
The prompts I gave are: “oil painting, still life, bronze vase, light pink roses, curtain, table, realism, expressive strokes, worn palette;” – basically, a Watts’ Atelier homework. The first result it returns contains 4 choices:
You can choose to further develop them and make variations till you are satisfied or give up. Some of the “final” ones:
Here are some of my Kandinsky (kandinsky with expressive bold strokes, fish, abstract colors) and André Masson (André Masson drawing, colored pencil, street musicians, metro, gloomy):
A few notes:
It’s a lot of fun. Thanks to the limited number of trials that I didn’t end up spending my life on it.
I don’t really know how to make the best out of this Midjourney. I have seen amazing artworks coming out of it. I assume the the prompts you give make all the difference, but I didn’t spend time digging what the algorithm handling better, more general or specific instructions, more or fewer words etc.
Also, if the attempts are not limited (with a subscription I assume), you can keep manipulating them. The result may get much better or worse.
If you are into digital art, this can be a tool, and if you are making abstract art, this can be a great idea generator.
But, who can claim the authorship? In a few pieces, there’s even an attempt of signature. Whose signature? It seems to me like Kandinsky or Mason. So does the algorithm aims at creation or imitation?
I also like the fact that in some cases the painting comes with a frame.
One thing for sure, if the big names in art history and all the prodigies online haven’t stopped us attempting new artworks, AI wouldn’t either. Back to painting! 🙂
My 2D Design class comes to an end and the final project is a poster designed as a tribute to an artist. As I mentioned in an earlier post, Wayne Thiebaud (b. 1920) is an artist I admire and want to study. So I took the opportunity to revisit some of his art:
All the images are paintings or sketches by Mr. Thiebaud. You can find his self-portrait, his portrayal of his wife, his best-known subjects, pies and cakes, and his typical landscapes – San Francisco streetscapes, Sacramento River Delta and mountains and many more. I also included one of my favorite quote from him.
I like Mr. Thiebaud’s vibrant but often economic use of color, his bold and whimsical composition, and above all, his ability to turn mundane subjects into humor and drama. There’s also a healthy positivity in his art, that always cheers me up.
Mr. Thiebaud just celebrated his 100th birthday this past November.The Crocker Art Museum in Sacramento curated an exhibition commemorated the event and Smithsonian has an interesting article about it. Obviously Mr. Thiebaud is still painting everyday, playing tennis and driving!
Would art do that to me? 🙂 Best wishes Mr. Thiebaud!
This is the painting that received the recognition:
I also submitted one to a different category, “Photography and Digital.” I don’t really have any experience with digital art. I took a watercolor doodle and manipulated it in Photoshop Express and Procreate. It failed to enter the show, understandably, but I had a lot of fun making it:
Maybe I’ll make a carpet out of it some day!
I am taking a 2D design class this fall and learning some basics about Photoshop. Hopefully I will have some better stuffs to submit next time! 🙂
Light, Space & Time has online exhibitions of various themes and it is cheap to enter. Highly recommend for emerging artists.