Lukman Febrianto

This is what I call a breakthrough, @Adobe and @AdobeFirefly. Big congrats! 🥳🎉 Thanks for sharing the latest info, Kris @icreatelife. AI image and video models from Chinese AI companies can generate stunning results at a much lower cost.

@henrydaubrez Stunning short movie, @henrydaubrez. Thanks for sharing it and the behind-the-scenes. Wishing you success! ☺️🙏

Junkyard King - Ep. 0 | MAKING OF ⚙️ HERE’S HOW I MADE THIS, STEP BY STEP 🧵👇 1/14

@carolletta What kind of music that you like @carolletta?...

It is time to flash your AI Art! Share your AI Art - Any subject Like 💛, repost 🔁, follow & tag @ your friends ⭐️!

@carolletta @grok Thanks for the confirmation, @carolletta. Happy creating ☺️🙏

@lukmanfebrianto @grok No! It is v7

Grok vs Midjourney Which one you prefer? Prompt Share on the thread 👇

@carolletta @Adobe @AdobeFirefly Thank you so much @carolletta . I really appreciate it... ☺️🙏

@lukmanfebrianto @Adobe @AdobeFirefly Amazing! ❤️ Well I will be selecting the winners soon! And you are on the list!

A little reminder of my love ❤️ for @Adobe @AdobeFirefly And I got 10 free vouchers of 3 months Firefly Pro membership to give away to my followers! ⭐️⭐️⭐️ Isn’t that really cool? Let me know who would like them and why ❤️ also post your best image!

@ryanlightbourn Congratulations on being one of the Honorable Mention winners in the @higgsfield AI Video Contest: youtube.com/watch?v=babNcx…

I’m a 42 year old former filmmaker. I made this in 3 days with $39 in credits because it was fun to channel the creativity I had in my 20s It entailed writing, directing, cinematography, art direction, SPFX, editing & sound design The kids will rock our world with these tools❤️

@azed_ai @midjourney Thank you Amira... ☺️🙏

@lukmanfebrianto @midjourney Absolutely amazing 😍

🖼️ Midjourney v8 Alpha Just Entered The Arena… How Good is It Now? I’ve always enjoyed creating sci-fi, fantasy, surreal, and abstract visuals with Midjourney—it’s incredibly strong in these styles. Today, I explored Midjourney v8 Alpha on the @midjourney platform, then generated the same creative direction using Seedream 5.0 Lite and Nano Banana 2 on @ImagineArt_X platform. Curious how each model interprets the same idea? 👇 Check the thread below to see the prompts and results—and share what stands out to you.

@carolletta @Adobe @AdobeFirefly I can use it for many other things, @carolletta. I'm a regular @Adobe CC subscriber with very limited AI credits. Having a Pro Membership would let me create complex scenes and short videos like this one: firefly.adobe.com/boards/id/urn:… Thank you... ☺️🙏

@lukmanfebrianto @Adobe @AdobeFirefly Wow! Beautiful 💙 But would you use it only for upscaling?

@javilopen @midjourney This is my other exploration with Midjourney V8 @javilopen ... x.com/lukmanfebriant…

@lukmanfebrianto @midjourney Terrible hands and anatomical problems. Glad we nano banana to fix it.

Midjourney v8 just came out, and I'm seriously disappointed. V7 left V8 right Seriously??? 😂

@midjourney Exploring with some prompts using Midjourney V8... x.com/lukmanfebriant…

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!

@azed_ai I share it here Amira @azed_ai ☺️🙏 x.com/lukmanfebriant…

Share your Midjourney v8 results 🔥💜

@icreatelife Awesome new feature Kris @icreatelife 😍. Congrats to @Adobe dev team... ☺️🙏

🎉 We just released Rotate Object in Photoshop (beta) 🎉 You can now rotate 2D images! 🤯 Then use Harmonize to add light and shadows, to blend it perfectly with the rest of the scene. It's like Turntable in Illustrator, but instead of vectors, it's pixels in Photoshop!

@dvorahfr Thank you for sharing your experience Deborah. You're absolutely right, each AI image model has their own way, how to understand and visualize the prompt... ☺️🙏

Prompting Tip: In a prompt, every word is important, and its placement within the prompt is equally important. You will get very different results from one AI to another with the same prompt. This doesn't mean that one AI is better than another, but rather that you need to use a specific vocabulary for each AI. I don't know of any other way than to test your prompts and modify them little by little to understand the importance of each change. This may seem tedious, but to my knowledge it is the only way to truly master the writing of your prompt and, above all, to get the best out of your AI.

@zeng_wt Awesome @midjourney exploration @zeng_wt 😍 Do you often use this image model more than any other image models?

Midjourney 👈 v8 👉 v7 - Speed is really fast, I love it! - Text is not 100% accurate, I have some generation with meh text (I think text rendering accuracy should now be the bare minimum any AI image model does well) - I prefer srefs in v7. The same codes in v8 look totally different. I’ll play with them more and maybe find some amazing ones.

@AllaAisling Awesome prompts and visuals, @AllaAisling. Any plans to categorize and compile them into a prompt book? I generated this image using your prompt template with Nano Banana 2 on @AdobeFirefly (Prompt in ALT). Is this image correct, Sir @elonmusk?

Prompt Studio: 3D Radial Explosion with Nano Banana 2 in Firefly Hyperrealistic 3D radial exploded view of [PRODUCT] [NUMBER] components bursting outward from a central axis in every direction, frozen in mid-air. True spatial explosion, not a vertical stack, depth and parallax visible. COMPONENTS (core outward): [SHELL] → [DISPLAY] → [FRAME] → [MAINBOARD] → [BATTERY] → [MICRO PARTS shown in 3x floating callout circles] MATERIALS: glass refracts and catches specular highlights, aluminium shows brushed grain and machined edges, PCB traces glow faintly amber, rubber gaskets matte with micro-texture, cables with soft bend physics. LABELS: hairline leader to floating box. "[COMPONENT]" uppercase / "[FUNCTION]" italic / "[KEY SPEC]" monospace. Radiate outward, no overlaps. LIGHTING: cool diffused overhead + warm amber underlighting on internals + thin blue rim on outer shell. Displays emit soft UI glow. Circuits self-illuminate. BACKGROUND: [COLOR], deep, non-reflective. Midnight black recommended. TITLE: "[PRODUCT NAME]" top right. SUBTITLE: "[TAGLINE]". SPEC BLOCK: "[SPEC 1] / [SPEC 2] / [SPEC 3]" bottom left in monospace. Mood: iFixit teardown meets NASA manual meets WIRED cover. 4K, tack sharp, extraordinary material fidelity. Check ALTs for ideas 👇 @AdobeFirefly

@EHuanglu Awesome 😍 The right man (or woman) behind the gun always create a masterpiece... 📷🙏

if this is what one person + AI can do.. what happens to the entire music industry?

✨ She Who Carries the Night Sky - Midjourney V8, Seedream 5.0 and Nano Banana 2 These images generated using the same prompt: A mysterious woman standing in complete darkness, wearing a deep hooded cloak that contains an entire galaxy—stars, nebulae, and drifting cosmic dust visible within the fabric, her face barely visible with soft starlight illuminating her lips and eyes, particles floating around her like constellations forming, surreal yet photorealistic rendering, extreme detail, cinematic lighting, deep shadows, 8K, studio-quality realism using 3 different AI image models: ✅ Midjourney V8 Alpha on @midjourney ✅ Seedream 5 Lite on @ImagineArt_X ✅ Nano Banana 2 Lite on @ImagineArt_X Which one that you prefer?...

🏜️ The Desert That Breathes Her Name - Midjourney V8, Seedream 5.0 and Nano Banana 2 These images generated using the same prompt: A mysterious hooded woman emerging from a vast golden desert, her cloak made of swirling sand forming and dissolving in the wind, ancient symbols glowing beneath the surface of the dunes, only her lips and chin visible beneath the shadowed hood, heat haze distortion in the distance, dramatic sunset lighting, ultra-realistic textures, cinematic composition, photorealistic, 70mm lens, high dynamic range using 3 different AI image models: ✅ Midjourney V8 Alpha on @midjourney ✅ Seedream 5 Lite on @ImagineArt_X ✅ Nano Banana 2 Lite on @ImagineArt_X Which one that you prefer?...