🤖 Greetings and welcome to Woollyfern! My background is genetics, data analysis & visualization (Python/R), and photography. AI generative tools have had such a positive impact on my ability to bring my creative ideas to life. My goal is to dive further into my creativity and share helpful resources and tutorials on AI generative tools along the way.
I’m 4 minutes in and it’s already better than every other Midjourney tutorial. Straight to the point and MULTIPLE references. This video is good for beginners but PERFECT for people like me who just needed a refresher and a cref tutorial. W video 🏆
SREF will only look at visual aesthetics. You might try using your image as an image prompt where the image URL goes before the text in your prompt. Check out this video on image prompting: ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-Kyr-nWtp1z8.html. I also show a brief example of using an image for posing when used with the Character Reference parameter in this video: ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-BOgqKKRT7IE.html
Setting a seed number tells Midjourney to start with a fixed "noise" pattern rather than a random one. It has very specific use cases. Most people never need to use it. Check out my article on the seed parameter for more info woollyferncreative.com/2024/02/26/how-to-use-seed-number-in-midjourney/
Patreon Community (free & paid tiers) ➡www.patreon.com/Woollyfern Midjourney Guides ➡ woollyfern.gumroad.com many are free and paid ones are included with some Patreon tiers
Hi! Setting a seed number tells Midjourney to start with a fixed "noise" pattern rather than a random one. It can be helpful when comparing prompts. It has very specific use cases. Here's an article I wrote about it woollyferncreative.com/2024/02/26/how-to-use-seed-number-in-midjourney/
Is it possible you have a typo in the muted whimsey style? I love your samples, but mine don’t look remotely like that-they’re dark, slightly surreal woodcuts
I found that the “beauty bias” extended to my cref model that I use constantly. Her freckles disappeared and her eyes have more glamorous makeup. I retreat to v6 when I use her for a more natural look. By the way, that’s both in photos and my preferred illustrations.
Thanks for these tips! I'll be applying them in my work tonight. @woollyferncreative Question at 04:58 , I didn't know a new Midjourney version changes the personalization 'id' P Code number. If so, can this be a way to reset errors? Like we just wait for the new version and run the personalization Task/Rank Images page all over to fine tune our style preference (mine is cinematic + photorealistic for my projects) from the previous Midjourney version? Thanks
For V6.1 they implemented an entire new model/algorithm for how they use our image pair ranking data to generate personalization codes, which is different from their personalization model for V6.0. Each new --p code since the V6.1 release is a reflection of all image pairs you ranked up to and including that date. Think of it as a snapshot in time in your image ranking journey. Your codes are not reset. Midjourney just has a new approach for trying to generate more accurate personalization codes. Hopefully that made sense!
@@woollyferncreative After I wrote the above question for you I went ahead and ran the the personalization Task/Rank Images page all over again but I only selected the images that looked like a real life-like photo, from food to people, from animals to cityscapes and one sci fi. I also selected realistic colors and moved away from neons images and those with sparkles. Then I used a prompt I ran in 6.1 last week to do some cover drafts for a writer. Same exact prompt in 6.1 and just now I got totally different results that resembled a still from a movie. So it works! 😀 BTW the prompt I used, if u want to test it, was for a pirate theme cover tests last week's came with bright intense tones, after rerunning today I got muted, very realistic colors and yes, the ID changed: Here's the prompt I'll erase it later- after I get the image I 2X zoom out and take it to Photoshop for fixes: a handsome athletic English cyber soldier pirate with dark hair in a science fiction azure skies, dark blue and dark black, in the style of Michael Garmash, realistic movie still, dark black and beige, soft-focused hyperrealism cinematic colors golden ratio, ambient occlusion, high key photography, arabesque sci-fi, towers, sci-fi futuristic minarets, walled sci-fi city, fortress gate, cinematic light, insanely detailed and intricate melancholy, Photorealistic, ultra quality, fashion style, Studio Lighting, rtx, shot on 70mm, in the style of john collier --ar 2:3
@@woollyferncreative Last message before I get back to 'work' doing AI art for three art-packed short story anthologies. The 6.1 revised new ID is doing more detail after a new personalization run than the 6.0. In that prompt one of the models has a sleeveless leather vest and only when I opened in browser and zoomed in notice the improvements. The hems are not just extremely well made but show irregular wear-and-tear in sections you don't see unless you zoom in: the leather vest has sections facing the front to detail wear and tear more, like weapons pockets, than sections where a person would barely touch or mangle if wearing a vest like the upper shoulder fabric. And the light on the vest matches the same source of light reflected on face and arms in same tones. And the best tiny detail, the exposed top of the arm under the sleeveless vest has a slight color variation, less tan, than the rest of the arm exposed to sunlight, just like any person going outside under the sun for hours and arms are tanner than skin under the shirt. I've never seen such miniscule attention to these color details before, and I only selected less than 100 images with photorealism under the personalization Task/Rank Images to override the 1,100 plus from the 6.0 personalization. So, it doesn't take much to get a new clear slate id. Bye and looking forward your next tutorial!
I think in a lot of cases the overall lighting is better for photographic images of people in 6.1, but yea, there's over-beautification much of the time.
MJ still overly exaggerates describing people. Anyone with a little extra baby fat is described as obese. It even uses phrases like fat ugly and obese which is extreme for many use cases for describing especially when you try to use the prompt and it says it goes against their standards
The prompt to text is slightly improved. It can't handle long phrases. Actually Leonardo ai Phoenix is superior. So far, I have not seen anything in V6.1 to brag about, but I'm confident in the long-term development.
Join the Woollyfern Patreon (free & paid options): www.patreon.com/Woollyfern Topaz Labs Free Demo Download (affiliate link): geni.us/kzlG Midjourney Guides: woollyfern.gumroad.com ➡many are free and paid ones are included with some Patreon tiers
hi I really have an important question, whenever I create a male character they always turned out to have wrinkle lines on forehead how to make midjourney understand not to give that line? I just can't seem to figure it, you never have that problem as I saw your video, would you please help me out, thanks
Can you give an example prompt? What types of age-related words are you trying to use? Alternatively, you can try to use Midjourney's inpainting feature called Vary (Region) to select the forehead area and it will redo it.
@@woollyferncreative oh I didn't know inpainting vary could do that, will check it out .I use the prompt like like this "a cinematic still of a man in his 30s is sitting in a coffee shop wearing black coat and pant with blue tie, coffee and laptop on the table, shot on blackmagic ursa mini pro, muted color grade." That's just one eg. But even if I make a person in his 20s, same with forehead lines. I would love to know if you face that issue from your end after trying my prompt. Thanks for the reply really appreciate 🙏
I tried your prompt. I do see that in some of the results, but for most of them it looks natural. I would try out the vary (region) tool or try using different words to give him a more youthful appearance. Sometimes MJ can exaggerate some descriptors such as age.
I use Photoshop to increase dpi. By default it increases image dimensions when you increase dpi, so you'd need to resize it after. Someone else might be able to suggest an alternative.
Some things are still much better in version 6...especially photo realistic images for photography...will see what V7 will bring...for now the 6 is better for me personally...
i would kill for real controlnet with midjourney, this has been my number 1 frustration with them is that you cant use MJ to reimagine your art--the '--iw' feature is close to useless, intentionally crippled by them for whatever reason. depth controlnets are the weakest too, would love to have an edge controlnet where you can re-skin your own art or concept in whatever style you want. its good for reimagining art/architecture etc. i get the hesitation of adding this as many people would abuse it but also youre cutting off the legitimate users as well. its basically the reason i only pay for leonardo ai these days, since their suite of controlnets is super powerful
There are some things that I like better in 6.1. I do see an improvement in things like eyes and skin texture. However, I prefer the more diverse, "normal looking" people I get with 6.0. 6.1 also feels a bit less creative to me? I'm still working this out via lots of prompt testing, but many of my 6.0 prompts seem to give me more simplified results in 6.1. I'll share some examples in my next video.
@woollyferncreative Re 01:16 how do you clear personalization to redo it again? I didn't know what I was doing when I clicked on 700 plus image likes from the two presented. When I saw a video, the likes grab that style as your preference, I try to correct it from then on selecting realistic sharp images over the neon, cartoon, etc ones or just passing on choices. End result my personalization became a bit messy, and I want to reset it. Any ideas?
I would contact their Support and see if they are able to reset it for you by deleting all of your previous rankings. I don't know if they can do this, but it's worth checking. Alternatively, you could spend a bunch of time ranking new image pairs and eventually it will outweigh your previous rankings.
@@woollyferncreative Thanks, the later seems to be faster! I do covers and AI art themes for books and the look I'm after is photorealism, especially in colors and sharp edges, over pop or comic book art. I tested it yesterday and now if I want to make cartoons, I have to remove my style preference, or all will look like a photo.
thanks for the amazing tutorial but I tried so much and the character dont look the same with cref, I dont know why, Ive tried cref, characterweight but I dont know what Im doing wrong
MidJourney version 6.1 feels more restrictive in terms of artistic expression compared to version 6. While both versions have their strengths, the natural, human-like artistic quality of version 6 is noticeably diminished in 6.1, making images appear more bland, similar to DALL-E 3. It's crucial for future updates to enhance functionality without losing the unique, expressive qualities that made version 6 stand out.
I totally agree. They acknowledged in a recent office hours that this could happen in 6.1, but are actively working to correct that when v7 is released. 🤞
@@woollyferncreative Awesome! Thank you for letting me know. This has been the best subscription platform I have ever used. They are "Steve Jobs" careful with change and consistency. I have noticed it’s been great with reference images when you're struggling with clarity on more organic-style artwork. So, at the moment, they are a nice yin and yang.
Thx. Adapting to 6.1 right now. Noticeable number of boobs out of guidelines I guess. Love --p 🤩 Good luck for Patreon (too much subs at the moment to add one sorry).
Yep, I'm still working my way through a bunch of different prompts to test it out. Thanks re: Patreon! Fyi - there is a free tier that will have content occasionally. 🙂
🌟What do you think of V6.1?? Join the Woollyfern Patreon ➡ www.patreon.com/Woollyfern Model Personalization ➡ ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-LESiAePjE4I.html Midjourney PDF Guides (free with some Patreon tiers) ➡ woollyfern.gumroad.com
Great video, thanks for sharing. I'm working every day on improving my AI content generations skills! Can't take off a week or something revolutionary happened 😅
There's a couple of examples in my CREF deep dive video here ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-BOgqKKRT7IE.html, I may make a dedicated video for that combo in the future. Thanks!
Thanks! You don't need to use seed number in your regular prompting. Here's an article I wrote on the seed parameter and it explains when I tend to use it woollyferncreative.com/2024/02/26/how-to-use-seed-number-in-midjourney/