F500 Consultant • Sr Product Designer by day, AI Explorer by night • Sharing daily AI learnings, prompts and insights
Master tech's softer side →
Joined April 2009
- Tweets1.6K
- Following205
- Followers499
- Likes3.1K
Pinned Tweet
I've been exploring the intersection of the technological and the organic for quite some time now, with #midjourney as a sidekick
With all the latest features being released, I wanted to revisit some old prompts, blend with diverse styles
📌This thread will be a long one…
#aiartcommunity #midjourney52 #AIart #AIArtworks #promptsharing
Slavina Ivanova retweeted
Midjourney Style Tuner First Run.
/tune an astronaut, neo-pop iconography, light purple and neon green --ar 2:3
Note.
I chose to generate 32 Style Directions, but MJ decided to generate 64 (maybe a bug?)
Click "Are you sure?"
Slavina Ivanova retweeted
📢 Introducing our latest research @Apple MLR for generating high-quality images & videos with a multi-resolution diffusion model -- Matryoshka Diffusion Models or MDM🪆, directly in pixel space (~1024px) without any VAEs or cascaded models. Code will be released soon! !(1/n)
Matryoshka Diffusion Models
paper page: huggingface.co/papers/2310.1…
Diffusion models are the de facto approach for generating high-quality images and videos, but learning high-dimensional models remains a formidable task due to computational and optimization challenges. Existing methods often resort to training cascaded models in pixel space or using a downsampled latent space of a separately trained auto-encoder. In this paper, we introduce Matryoshka Diffusion Models(MDM), an end-to-end framework for high-resolution image and video synthesis. We propose a diffusion process that denoises inputs at multiple resolutions jointly and uses a NestedUNet architecture where features and parameters for small-scale inputs are nested within those of large scales. In addition, MDM enables a progressive training schedule from lower to higher resolutions, which leads to significant improvements in optimization for high-resolution generation. We demonstrate the effectiveness of our approach on various benchmarks, including class-conditioned image generation, high-resolution text-to-image, and text-to-video applications. Remarkably, we can train a single pixel-space model at resolutions of up to 1024x1024 pixels, demonstrating strong zero-shot generalization using the CC12M dataset, which contains only 12 million images.
Slavina Ivanova retweeted
Midjourney Office Hours 09.27.23
A quick recap.
v5.3 (next version)
- aesthetic personality tests - help customize your image making
- upscaler in the works (2k x 2k)
- estimated release in October
- playing around with color e.g. HEX code release
- possible aesthetic improvement (would/could call it v5.5 - if released)
v6
- better image quality, better language understanding, better blends, better resolution
- bigger batch size (maybe 2x or 4x)
- 4-8 weeks? (unlikely to come up in October)
Website
- approaching Phase 1 release of the website
- better lightbox, better design (new codebase)
- phase 1 will not have image generation
Other
- may ask users to describe pictures in detail for fast hours
- working on 3D and video, will likely release 3D first (before video)
. . .
In case you miss these recaps here, you can find them on my website and in my Creative AI newsletter (link to subscribe in my bio).
Slavina Ivanova retweeted
See you lovely people soon 🙏
Join us for the Generative AI Friday 𝕏 Space to hear the latest updates with some of our friends:
@saana_ai
@spacecasetay
@Salmaaboukarr
@LinusEkenstam
& many more.
Don't miss the best Gen AI conversation on 𝕏.
Set your reminder 👇
teapawt.net/i/spaces/1yoKMwRDbPWJQ
Slavina Ivanova retweeted
BREAKING: YouTube announced a suite of AI tools for creators! From a dedicated video editing app and AI language dubbing to AI video generation and ideation. Here's the TL;DR:
1. AI Video with Dream Screen - Visually transport yourself anywhere by typing a prompt. This new Shorts feature generates fantastical backgrounds in both image and video form.
2. Free Editing App YouTube Create - A free mobile app provides easy professional editing tools to craft high-quality videos in minutes. Perfect for first-timers and looks like CapCut has competition.
3. Personalized AI Insights - Get tailored video ideas and outlines in YouTube Studio based on your channel and current trends. Over 70% found it helped generate creative ideas. Can't wait to try this!
4. Auto-Dubbing with Aloud - Use AI dubbing to automatically localize your videos into other languages with one click. Expand your audience globally.
5. Assistive Music Search - Instantly find the perfect free soundtrack by describing your video. AI recommends songs and beats that fit best to your music.
Can't wait to give these a whirl! YouTube is obviously the 800 pound gorilla in online video, and with Shorts now driving 70 billion views on a daily basis - these tools will make a difference in fueling that demand.
If you enjoyed this post, you might also enjoy my feed: @bilawalsidhu
Slavina Ivanova retweeted
ANYONE can animate AI generated images in less than a few minutes 👏
Clients always ask about this. "These images are great but is there anything like this for video?" YES!
11 of my favorite AI animation tutorials / workflows 👇
Slavina Ivanova retweeted
Join us for the Generative AI Friday 𝕏 Space to hear the latest updates with our friends:
@saana_ai
@chaseleantj
@spacecasetay
@Salmaaboukarr
@LinusEkenstam
Don't miss the best AI conversation on 𝕏.
Set your reminder 👇
teapawt.net/i/spaces/1BRJjZgmyOaJw
Slavina Ivanova retweeted
Hot off the presses! Straight from @pika_labs Announcements Discord Channel, buckle in!
NEW FEATURE's Available to ALL:
Control the camera movement using our -camera parameter. This parameter accepts ONE of the following motion types:
- Zoom: Use -camera zoom in/out.
- Pan: Use -camera pan up/down/left/right. You can
combine two non-conflicting directions, e.g., -camera
pan up right.
- Rotate: Use -camera rotate
clockwise/counterclockwise/anticlockwise or the
abbreviations cw/ccw/acw.
Remember: You can still adjust the camera motion intensity using the -motion parameter.
Other Updates (!!):
The default value of -fps has been adjusted to 24.
Slavina Ivanova retweeted
Join us for the Generative AI Friday 𝕏 Space to catch up on the latest news with our friends:
@mreflow
@saana_ai
@bilawalsidhu
@spacecasetay
@Salmaaboukarr
@LinusEkenstam
Don't miss the best AI conversation on 𝕏.
Set your reminder 👇
teapawt.net/i/spaces/1RDxlaAYmadKL
Think of your creative journey as a lantern
The clearer your purpose, the brighter it shines
GN🖤🤍
#midjourney #AIArtworks #aiartcommunity
What if the only thing grounding you is the weight of your own doubts?
GM ✨
#aiartcommunity #AIArtworks #AIart #midjourney #promptsharing
ALT levitating, translucent, dreamy lights, mother of pearl blobs
1
6
235
Great recap as always! Thanks, Alie!!
Midjourney Office Hours - Aug 9, 2023
v5.3
- possible release next week
- inpainting and aesthetic - in Discord
- may be only available on desktop
v6
- working on it, adding more performance
- will be more coherence, better language understanding
- the grid size may change, but not sure yet
(internally they use bigger grids e.g. 4x4)
- no estimated release date at this point
Website
- a lot of people working on frontend of the website
- will be both for desktop and mobile
- launch date is getting pretty close, but no specific date at this time
- Explore will be much better
- Create page will be much better
Surveys - Research
Interesting results from data
- 80% male users
- people who are rating images are older users
- male and older user biases in the ratings
- interesting differences e.g. male vs female, and older vs younger aesthetics
For example:
Females - prefer more of a v3 type look/aesthetic, males - high contrast aesthetic
Geographic differences
- e.g. Japanese vs. Europeans have different aesthetic preferences
- difference even between, e.g. Germany and UK
MJ has a feedback loop where it learns a bit from the community, so it can have users' biases. They have started to look at this and start detangling things.
They will publish results and stats later.
Other
Sometimes this month may test a 2x speed for the pro and mega tiers.
Storytelling research.
Working on video. No specific timeline.
Secret project (as usual).
No API anytime soon.
111
GM ✨
When Monday got you tangled into its blues - keep levitating!
💠 Prompt: Monday blues
#aiartcommunity #midjourneyartwork #AIArtworks #promptsharing
3
175
GM ✨
Old ways won't open new doors - stay curious!
Sneak peek of something I've been exploring and will be posting here soon
#aiartcommunity #midjourneyartwork #AIArtworks
146
Slavina Ivanova retweeted
Today, we are evolving Photoshop's Generative AI capabilities with Generative Expand. There is no need for selections; use the crop tool to expand the canvas, hit enter, and #AdobeFirefly will do the rest. Update or download the Photoshop (beta) now: adobe.ly/psww
Slavina Ivanova retweeted
Friday is BACK!
This is the best AI group- come hang out 😎
teapawt.net/i/spaces/1BdGYyyOyjMGX