Misfits Studio

So happy to announce the selection of my work for exhibition: “Cradle, Homage to Constantin Brâncuși” (2026) now showing in the second annual edition of HOMAGE a tribute to Constantin Brâncuși* March 19 - April 14, 2026 Marin Sorescu National Theater, Craiova, Romania (tncms.ro) Presented by @ArtBeesGallery, Romania’s first NFT gallery (artbeesgallery.art) Curated by @ErikaRand and @NONE32X32 Supported by @Foundation *Works will also be minted on ETH and sold in the HOMAGE Exhibition on Foundation, date to be announced. ____________ This work is an extension of my recent Fall 2025 collection titled "Frags", which revealed AI’s perceptual logic sculpted into light and motion. A branch of my aesthetics research "Project Native," the Frags take the form of short, looping videos that capture the uncanny moment when AI fabricates unseen surfaces and recalculates how light and color refract through them.

@Pa3loChaco and the subliminal frames

@Pa3loChaco gm, Pablo love what you’ve been doing

gm☀️

just an experiment house always wins @Midjourney v8 (text prompt only) —> Grok Imagine

Many thanks 🙌🙏 to collector 0x0718E…849B for recently collecting Sway through Fellowship—as well as for collecting Frag 002 on secondary!

This video work imagines a sculptural vessel holding the landscape of Brâncuși’s birthplace in the Carpathian Mountains. A single, reduced glass form contains the mountains, sky, and drifting clouds, as light slowly shifts within it. The work reflects on Brâncuși’s search for essential form: rather than describing the landscape, it is distilled into a quiet archetype of origin. The sculpture becomes a cradle — a form that holds beginnings. As clouds move through the contained horizon, the surrounding light completes the sculpture, echoing Brâncuși’s belief that material and light together reveal the spirit of a form. The piece offers a meditation on birthplace, memory, and the way a landscape can live within a form long after we leave it. It is also a tribute to my Romanian family by marriage, who have endured many hardships over the decades, but always with dignity, resilience, and love.

So happy to announce the selection of my work for exhibition: “Cradle, Homage to Constantin Brâncuși” (2026) now showing in the second annual edition of HOMAGE a tribute to Constantin Brâncuși* March 19 - April 14, 2026 Marin Sorescu National Theater, Craiova, Romania (tncms.ro) Presented by @ArtBeesGallery, Romania’s first NFT gallery (artbeesgallery.art) Curated by @ErikaRand and @NONE32X32 Supported by @Foundation *Works will also be minted on ETH and sold in the HOMAGE Exhibition on Foundation, date to be announced. ____________ This work is an extension of my recent Fall 2025 collection titled "Frags", which revealed AI’s perceptual logic sculpted into light and motion. A branch of my aesthetics research "Project Native," the Frags take the form of short, looping videos that capture the uncanny moment when AI fabricates unseen surfaces and recalculates how light and color refract through them.

@Pa3loChaco thanks, Pablo If I see any installation views of the exhibition, I will let you know. I think Blackdove may be assisting with screens, but not sure.

@Barbara_Chira amazing Barbara!! curious to see how your work is being presented!

@Pa3loChaco Thanks, Pablo! It was in one of your X spaces in the past several months, in which you discussed how work might be shown or shared outside of the NFT and X spaces, that I began considering the possibilities.

@Barbara_Chira congratulations Barbara!!!!

@EstebanAmaroArt Thanks so much, Esteban, for always your generous encouragement.

@Barbara_Chira Happy to see this, great piece friend! Congrats!

@sinusoidalsnail 🫶🙌🫂

@Barbara_Chira That’s so wonderful! So deserved! It’ll be fantastic 🖤🖤🖤

@Sloposaurus @midjourney I think maybe I mean the other way around: generate in 8 and then edit part of a v8 image using v7.

@Barbara_Chira @midjourney That’s interesting. I would not have assumed 8 would enhance 7. 🌟

Working on a music video and along came @midjourney v8 today. For my prompts and what I envisioned, v8 has been far superior to v7 thus far. Version is indicated in the lower rights corners. Some of the highlights for me include the non-frontal non-symmetrical composition in the casino image (a diagonal!), although I do like that ceiling in the v7 image, and the prompt adherence in the final image. The prompts were long and detailed.

@sinusoidalsnail Thanks, Sine! I think it’s the first physical exhibition of my AI video work.

@Barbara_Chira Congratulations Barbara! So awesome! 🖤

@Sloposaurus Thanks, Slopasaurus!

@Barbara_Chira Congratulations! That’s outstanding. And such beautiful work. 🎨

@Sloposaurus @midjourney Thanks. Working back and forth, through the MJ editor, from V8 to V7, is also productive.

@Barbara_Chira @midjourney The V8 looks fantastic.

@EstebanAmaroArt gm ☕️

Gm 👁️ “Water Portals 061” A piece from my vault, now relisted.

@SHL0MS Yeh, I work back and forth. MJ first and then Nano to insert things, change things, etc. in the MJ images.

i just want something with the prompt control of Nano Banana and the aesthetics of Midjourney is that too much to ask

@alanxtruc Agreed.

Midjourney V8 alpha came out last night. A lot of people seem disappointed, but I suspect this has more to do with prompting habits than with the model itself. Many expected Midjourney to become something like Nano Banana with a "Midjourney aesthetic filter" on top. I doubt that is its direction. The particular aesthetic of Midjourney is also what makes its prompt understanding different. Perhaps less literal than some other image AIs, but with an aesthetic that is vastly superior to most others. There is probably a trade-off here, and I suspect it will remain that way. What they improved in V8, however, is prompt understanding. In my tests it works noticeably better. In short, it is Midjourney, but slightly more realistic, and much better at following complex prompts. One thing you should know is that my approach is very peculiar and minimalistic. I treat Midjourney the same way I treat photographic equipment: I just use it as it is. I rely almost entirely on text prompts, elaborated ones. I rarely use srefs, moodboards, or other layers of control. That makes the workflow much more stable across versions and better overall. I almost don't reroll. This image is a good example. A complex spatial situation described only with text. In previous versions Midjourney struggled with this kind of spatial logic. V8 understands it. Cheers @midjourney, still the best for artists.

Fellowship x @artxcode_io at @ArtBasel: RECURSIONS 遞迴 by @sougwen This year at Art Basel Hong Kong, we are presenting RECURSIONS 遞迴, a new live work by London-based artist Sougwen Chung, as part of Zero 10, the fair’s platform dedicated to new media and digital art. The presentation reflects our ongoing commitment to artists working at the intersection of advanced technologies, embodied practice, and contemporary image-making. ↓ Here’s a short introduction to what you’ll see at the fair

@fellowshiptrust Many congratulations, @trevorpaglen. 🎉

Trevor Paglen Selected as the 2026 LG Guggenheim Award Recipient Guggenheim New York and LG proudly announce Trevor Paglen as the 2026 LG Guggenheim Award recipient. Paglen is the fourth artist to be recognized as part of the LG Guggenheim Art and Technology Initiative, a five-year, multifaceted collaboration designed to research, honor, and promote artists working at the intersection of art and technology. Paglen will deliver the lecture-performance "The Lizard People Are Here!" at Guggenheim New York on May 18. Please visit guggenheim.org/calendar/ for more information.

Working on a music video and along came v8 today. For my prompts and what I envisioned, v8 has been far superior to v7 thus far. Version is indicated in the lower rights corners. Some of the highlights for me include the non-frontal non-symmetrical composition in the casino image (a diagonal!), although I DO like that v7 ceiling, and the prompt adherence in the final image. The prompts were long, detailed and precise. Also, the v7 results came after many reruns and edits. V8 results are from the first batch of 4 images.

A much longer followup V8 post from our blog: Hi everyone! Today we’re letting the community test an early version of our V8 model on alpha.midjourney.com. We want your feedback and your help. Let’s explore what this new model can do. V8 is an incredible model. It’s much better at following detailed directions and will still surprise you when you ask. Its ability to understand your aesthetics through personalization, style references (srefs) and moodboards is amazing. Images are more coherent and detailed. Text rendering works better than ever (when specified in “quotes”). And image generation is ~5x faster than before. We’ve upgraded our web interfaces to support this speed. And more is coming. We have an improved conversation mode so you can just ‘talk’ in flow, a “Grid Mode” so you can focus on a single big set of images, and we’ve moved our settings into ‘sidebars’ so you can tweak settings without blocking your view. V8 launches with support for multiple aspect ratios, --chaos, --weird, --exp, --raw. We support backwards compatibility with your V7 personalization profiles, moodboards, and srefs. V8 brings a new --hd mode which natively renders images at 2K resolution and a --q 4 mode if you need a little bit of extra coherence. Modes and Pricing: Presently, Relax is not yet supported. We are working on a new server cluster for Relax plus cheaper render modes. --HD, --Q4, SREF, and Moodboard jobs are 4x as slow as regular jobs and each costs 4x (for now). The best way to help us improve V8 is to rate images in the lightbox. Click an image in create then click “I like this image” “I don't like this image” on as many of your V8 images as possible. You can use 1/2/3 hotkeys and arrow keys to rate images quickly. Other Tips and Tricks: If you’re going for photos or a more ‘plain’ or ‘in control’ look we’d recommend switching to --raw right away or using moodboards or srefs to control your style. We’re still working on the ‘default’ aesthetics of V8, but we strongly encourage you to use your personalization and even crank it to –stylize 1000 asap. V8 is going to shine most right now when you rely heavily on our stylization systems and when you trend towards longer more specific prompting. Please Note: This is an entirely new model with unique strengths and weaknesses, we want to learn from you what it's good and bad at but keep in mind it may require totally new prompting styles. So play around a bit! It’s time to play! Show off what you’re making in #v8-showcase and let us know what you think in #ideas-and-feedback. As the model becomes more mature, we’ll do a community-wide roadmap ranking session to help us figure out what to prioritize next. Thanks again for everyone’s help with the V8 pre-release rating parties, and thank you so much for being a part of Midjourney! Let’s have fun out there and find new wonders on this vast and shared sea of imagination.

Today we're starting to test an early version of our V8 model with our community. It's much better at following prompts, 5x faster, has native 2K modes, improved text rendering and the best personalization, sref, and moodboard performance ever. Have fun!