Here are some side-by-sides of my prompts, v4 vs v5, as well as some new prompts and crowd shots. I'll add more to this as I experiment.
🧵
Editorial Style Photo, Eye Level, Modern, Living Room, Fireplace, Leather and Wood, Built-in Shelves, Neutral with pops of blue, West Elm, Natural Light, New York City, Afternoon, Cozy, Art Deco --ar 16:9
v4 (left) v5 (right)
1960s street style photo of a young woman, sitting, sailboat, green dior dress, silk green dress, green dress, silk, pearl necklace, tiffany's pearls, tiffany's pearl necklace, sunset, ocean, shot on Agfa Vista 200, 4k --ar 16:9
v4 (left) v5 (right)
Crowd Shot
1960s street style photo of a crowd of young women standing on a sailboat, wearing dior dresses made of silk, pearl necklaces, sunset over the ocean, shot on Agfa Vista 200, 4k --ar 16:9
street style photo of a young woman, red gucci jacket, blue gucci shirt, wide shot, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9
v4 (left) v5 (right)
Street style photo, Closeup shot, Nike Air Force 1 slytherin collab, unique Colorway, snake skin, hogwarts, natural lighting, original, unique, 4k --ar 16:9
elves working in a new york city bodega --ar 3:2
1990s era, photo of a young man, sitting, mechanical keyboard, working, desk, 1990s CRT monitor, monstera, 1 glass of oj, juice, wide shot, side view, natural lighting, home, polaroid, 4k --ar 16:9
1940s sci-fi film, wide angle, Ektachrome, a woman leading an army of art-deco style robots, chrome gucci spacesuit, retrofuturistic dusty courtyard, metal, gold, diamond, muted color palette, natural lighting, daytime, retrofuturistic, vintage, retro, 4k --ar 16:9
👈 v4 v5 👉
Editorial style photo, top-down camera shot, blue Mercedes-Benz SL-Class 1963, coastal road, beach, sunny lighting, elegant, refined, iconic, 4k --ar 16:9
Follow me @nickfloats
First vid coming to YouTube this week
I'll be adding to this thread with more cool examples and new prompts.
street style photo of a woman selling pho at a Vietnamese street market, sunset, shot on fujifilm --ar 16:9 --v 5
street style photo of a busy new york city bodega filled with people standing by the deli counter --ar 16:9
Full prompt in ALT
v4 (left) v5 (right)
closeup shot of a woman playing the violin in an orchestra, focused and confident, shot on fujifilm --ar 16:9
Landscape Style Photo, wide angle, Eye - level, Colorful flower foreground, Redwood Trees midground, Mountainous background, Sky and clouds, Lush Natural Colors, Yosemite National Park, Spring, Sunset, 4k, Stunning, Breathtaking --ar 16:9 --seed 180392413
v4 left v5 right
Playing with the aspect ratio
a beautiful drone shot of the New York City Skyline, Rainy Day, overcast --ar 3:1
overhead food photography, Bibimbap, Korean restaurant --ar 16:9
I could go on forever but I’ll spare you for now. I’ll be posting much more over the coming days as I continue to experiment. Follow me @nickfloats for that.
Now im gonna go reshoot some YouTube footage to update everything for v5 😑 channel link in bio, vid coming this week
kodak disposable camera photo of a group of elderly women shopping for colorful spices at a crowded Indian street market, golden hour --ar 16:9 --stylize 0
I started adapting my prompts to v5 and put some examples here if you wanna check them out. Natural language makes a big difference.👇
I ran a bunch of random prompts through Google Veo 2
It's the best text-to-video model out right now
some non cherry-picked results:
An over-the-shoulder medium shot of an artist working quietly in a cramped, dimly lit attic studio, illuminated by a single overhead lamp. The painter’s brush gently glides over the canvas, each stroke reflected in their intense, focused gaze.
A front-facing medium shot inside a bright, minimal studio with white floors and walls. A ballet dancer moves in slow motion, each graceful leap and spin captured with crisp, high-key lighting.
Elaborating on how to use Midjourney's "Style Reference" feature
This is how you break free of MJs default training data "aesthetic", and fine tune the way it interprets your prompts
Codes & examples 👇
When you use the style reference feature, you're essentially sending MJ to a specific location in "style space"
Each location has its own unique style, vibe & aesthetic. Once you're there, any prompt you run will be influenced by the locations unique characteristics
It's a far more visual & interesting way of working in MJ
To navigate style space, you'll need:
> a style "code", or
> an image reference
Whether you use a code or an image doesn't really matter. They are effectively the same thing – coordinates to a particular "style"