(2/6)The tricky part is keeping our character consistent while applying variations.
So let's do just that. Copy the URL of the initial image (ensure to open it on browser first), use /imagine prompt:, and then paste the same prompt as before. But let's add a little modification
(3/6) Now, do the same, maintaining the original image url, but modifying his status. Lets say... bowing!
(4/6) And keep going on! Now Jimmy is prepared to run
(5/6) We can also add accesories, such as sunglasses
(6/6) I know the results can be improved, but certainly this can greatly accelerate the process of designing characters, animations... Give it a try and let me know!😊
• • •
Missing some Tweet in this thread? You can try to
force a refresh
Download a meme, use IMG2IMG with the maximum weight and the RealVisXL model. A simple prompt and Facemix with your face! Here's the step-by-step video 👇
In 2023, I've shared with all of you over 700 prompts, guides, and tutorials for MidJourney. And 2024 will be even wilder!
I've selected my top 🔟 prompts to see how they turn out with v6.
🏷️ Bookmark now, thank me later! 😉
#PromptShare #MidJourney #AIArtCommunity
1⃣ Colorful illustrations
A silhouette of a [subject] with a [background] background, a lively pond, in the style of simple, colorful illustrations, drugcore, bulbous, [colors], realistic forms, animated gifs, [extra details] --ar 16:9 --s 50 --v 6.0
2⃣ 1st person POV
A photo from first person POV, showcasing a [scene], with a focus on the diver's hands [action+object], from the angle --ar 16:9 --style raw --s 120 --v 6.0
1⃣ Significantly improved accuracy in prompt tracking and support for extended prompts. Improved coherence, and model knowledge
Look at how the image aligns much more closely with the prompt than in previous versions! You can find the example prompts in the ALTs.
2⃣ Improved image prompting and remix
Using "Vary" now has much more power, as the images maintain better coherence. In this example, you can see how, by changing the vehicle in the original prompt from a van, the images maintain much more consistency.