main global
34 posts
@SkyReelsAI1 are you gonna opsource it or not, just answer if you're not just say no, community want an answer, it's ok if you're gonna close it just say it ffs please.
English
The prompt is here.👇
Extreme macro shot, a delicate glass sculpture of a blooming lotus flower being shattered by a high-speed bullet made of glowing neon-pink liquid. The liquid violently splashes and refracts light through the flying glass shards. Pitch black background, volumetric laser lighting, hyper-realistic fluid physics, 1000fps slow-motion, native 1080P.
English
Give me a video prompt that you’ve NEVER been able to generate perfectly with other AI tools. 👇
I’ll pick the top 3 hardest prompts from the replies, run them through SkyReels-V4’s native 1080P engine, and post the results.
Don't hold back. Give me your craziest fluid dynamics, extreme lighting, and high-speed collisions. Let's go! 🔥
English
@side44412380050 @wildmindai hahah so funny so its cherrypicked?
English
some cool stuff from Google!
Dropped an Interactive Video Super-Resolution - SparkVSR
- CogVideoX1.5-5B;
- propagates high-quality textures from edited keyframes across sequences;
- tops DOVE and STAR, +24.6% on CLIP-IQA and +21.8% on DOVER;
- zero-shot restoration, colorization, style transfer!
- beats FlashVSR
sparkvsr.github.io
English
@aguiarpsd this i higgsfield.ai/app/relight relight from higgsfield this guy as many others are just post engagemetn farming, should take that as a lesson so less people would fall in future
English
@Elaina43114880 who hired you, who do you work for for posting ai slops retard gpt written clicking and baiting son of cringe, nobody cares aboud closed source model u dumbass ai newcomer.
English
Wan 2.7 is coming soon! A major all-around upgrade over 2.6! 🙀
What can we expect?👀👇🏻
- first-frame & last-frame video generation
- 9-grid image-to-video
- subject + voice reference
- instruction-based video editing
- video recreation / replication
There are still two weeks left in March, and there's still so much possibility! 😸
Alisa Qian@alisaqqt
Wan 2.7 is planned to launch within March — and it’s a major all-around upgrade over 2.6. Wan 2.7 will support: - first-frame & last-frame video generation - 9-grid image-to-video - subject + voice reference - instruction-based video editing - video recreation / replication A more powerful and comprehensive creative workflow is on the way.
English
Subscribe to Map the World by Bilawal Sidhu, by @bilawalsidhu spatialintelligence.ai/?r=7u76i2&utm_…
English
@LumaLabsAI don't you have a discord server was about to ask a question to know if i can join you for my sidehustle biz, but found no community plateform, you should make one.
English
@zasuko_michiksa cannot upload my own video reference for the pose to generate any solutions?
English
Mixsmoのモーションデータから任意の角度と
カメラワークでアクション動画化する実験👀
（RTX4090：VRAM24GB 環境）
なんとか成功！🙌
今日のライブ配信ネタはこれにします！
＜ComfyUIで加工＞※無料で完結
Mixsmo→アクションディレクター→Wan2.2 Animate
日本語
@AIWarper fake this guy been spamming lot of post to infect people
x.com/TzDev_/status/… see ex:
just all report him that's all, he has a second account or he's with friends doing same thing to infect max people
Matthew@TzDev_
Meet Pose Studio 😲 Create any pose and generate that scene with anyone in seconds. Now available in Adventure AI. Link in the comments ⬇️
English
@zer0int1 hi i want to contact you im a comfyui user and wanna discuss about clip vision models, i think i need some help, any contact, telegram discord or anything else thanks as it's urgent.
English
So that's what adversarial noise in an audio encoder sounds like? 😂
Ascending CLAP (Contrastive Language-Audio Pretraining). It won for these (the Text Encoder assigned >0.8 cos sim match for target label).
It's about as weird as an uninterpretable adv glitch-image in CLIP. 🙃
English
@EHuanglu no care show the process how to do it or dont post
English
@ModelScope2022 no one cares, base model is accessible for limited cn users as well as me it's overrated, same thing for the edit, they just selling at this point and lot of cn users are at talking abt a possible closing source of their best train model which they're not gonna release, same song
English
How I made $34k gmv in just 5 minutes:
Tiktok Shop is actually easy if brands are using my system.
It’s literally plug and play once brands are working with the proper fit creators
High GMV creators with product in hand are getting insane results
Best part is brands aren’t wasting samples
No wasted ad spend either
And actually able to get results quite quickly with agents
It’s fired a $500k marketing team
And made scaling on tiktok shop insanely easy
Best part?
I’m giving away the Agent away for FREE
My team begged me not to
But comment “SYSTEM” below and I’ll dm it over
P.S. Repost for early access
English
@MainGlobal20804 I did it by manually modelling the helmet. Tracking it on the head by manually animation and then composite, color correction and post effects using Nuke. Basically Hollywood VFX pipeline.
English
And here it is folks! DEADPOOL AND WOLVERINE FIGHT MASK EDITION! This one was challenging but I'm glad how it turned out! #DeadpoolAndWolverine
English
@TaranStingVFX1 may i contact you on telegram /discord anywhere i need to talk with you pro please, it's really urgent, and btw im working on comfyui mostly.
English
@8bit_e hi interestin work, mind sharing the process and the workflow? (tool + process) wanna gain some time in my pipeline, i can share recents info im working one np. have others socials to chat, (tgram, discord, whatever)
English
Another example of using masking to add elements into a scene.
For this one, I used ComfyUI with Wan 2.2 Animate and masking to fill in the area where Wolverine’s mask would be.
For me, using AI in subtle, surgical ways is the key. It helps keep things more convincing instead of feeling overdone.
I know people will nitpick it, and that’s fine. I’m just excited to explore what feels like the future of VFX.
English
Nano Banana Pro + MassContent + MassUGC = AI vid factory
this is the gritty process of:
-> setting up 200 accounts
-> automating 600+ AI posts per day
it's the dark funnel powering organic brands rn
like, rt + comment "DARK" for the 2026 mass content factory playbook in dms.
English
main global retweetledi
