neb
@nebsh83
Followers
383
Following
7K
Media
761
Statuses
4K
Music enthusiast |making music video (check my website) 😀
Joined January 2017
🎥✨ Reflecting on my first year as a music video creator! Proud to share the official videos I've had the privilege of creating. A thread 🧵👇 #MusicVideo #FirstYear Goldmoon feat Imany - RUN
6
2
5
Introducing MULTI-FRAMES — a major step forward in controllable video generation. Define up to 10 keyframes and generate a coherent one-take sequence up to ~54 seconds. Transitions can be set from 1–6 seconds, with prompts to control how each scene evolves between frames.
26
49
318
Voting is happening for the first edition of The Arca Gidan Prize! There's some extremely impressive work there from artists who are using open models to truly carve their own paths. If you have time, your attention/votes would be appreciated! Link below, trailer attached.
Introducing The Arca Gidan Prize, an art competition focused on open models. Supported by @ComfyUI & @banodoco, our goal is to provide a reason for people to push open art models to limits. Winners fly to Hollywood to show their piece to industry leaders/open source nerds!
1
2
19
Veo 3.1 & Sora 2 are live on CapCut⚡️ Hollywood-level AI video models, now at your fingertips. Generate cinematic stories, edit with precision, all in CapCut. Enjoy your limited-time free trial! Retweet to get 1000 credits in your DMs (24h)
106
282
252
I think #12 is actually working! After 6800 steps, something started to click! Here's a video explaining what i'm trying to do + results featuring a rare POM selfie as thanks for your prayers 🤲
I’m about to run my 12th/13th training runs for a new QwenEdit Lora that’s holding up me launching a whole new tool I think this version will do it but I also thought that for the last 11 Pray for POM 🙏
2
2
31
Your multi-cam rig is now a button. No extra sites, no weird workflows. Just ByteDance’s Seedance Pro, smoother and better here than anywhere else. 30+ ready presets with unlimited FREE gens for a week. Only in Higgsfield @higgsfield_ai
37
58
637
Guess Higgsfield hired another similar intern immediately, because they just sent me a similar offer - today. This isn't an isolated incident. I will no longer associate with Higgsfield. They seem to be very bad actors.
Higgsfield offered to pay an artist for views he gets on Sora 2 videos He made a few viral videos & asked for payment but they said they won’t because it was a now-fired “intern” who made the offer He then deleted the post, perhaps due to a threat - anonymised screenshots
19
10
134
Something BIG is coming for our most passionate creators. We’re about to launch the LTX Ambassadors Program, a new way to get early access, shape what we’re building, and get paid. Retweet and we'll DM you an invite to join the waitlist. Details + creator showcase below 🧵
137
437
523
We're releasing ✨Qwen Image Edit Relight✨ a dedicated Qwen Image Edit app for image relighting fast, precise and optimized for relighting no more need for a complex workflows when you can get sota outputs with as little as 8 steps
3
54
361
Today’s the day🚀 We’re opening the doors to the Daydream platform - API + Playground Experience🌊 We’re the world’s first hosted StreamDiffusion platform: 1⃣ No GPU required 2⃣Sub-second latency 3⃣Advanced controls that let you experiment quickly and scale seamlessly. This
13
35
100
🔥1-min Interactive Video Generation with Multimodal Control🔥 Towards *long-context world model*, #LongVie is an end-to-end autoregressive framework for controllable ultra-long video generation - Page: https://t.co/kKNHhjEmrl - Paper: https://t.co/M5wGkpi0Ve . Thanks @_akhaliq
What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵
0
36
148
Still testing WAN 2.2 and I’m amazed by its seamless scene cuts and transitions. The way it interprets prompts and follows complex, precise movements is equally impressive. @Alibaba_Wan 👁️👁️
0
0
4
New Zuck post, what a difference a few years makes: Today: "We'll need to be rigorous about mitigating these risks and careful about what we choose to open source." 2024: "Meta is committed to open source AI... and therefore a platform that will be around for the long term."
56
64
697
Overfed Dream (Hollywood, please stop with movies sequels). Another video test with @Alibaba_Wan 2.2
0
0
0