Musician & producer 🎛️

Joined January 2025
212 Photos and videos
Pinned Tweet
🔥 1 HOUR DnB MIX | 172 BPM Wide. Cinematic. Crushed. Oppressive. Turn it up loud. #DnB #DrumAndBass #DarkDnB #172BPM
1
5
245
🔥 New Project: axonis_video_engine I’ve been building a dual‑model video pipeline using WAN 2.2 Qwen 3.6 on a 4×3090 rig — but here’s the twist: GPU 0 1 = Qwen 3.6 (orchestration) GPU 2 3 = WAN models (video generation) The pipeline: 1️⃣ TI2V‑5B → generates multiple 2‑sec cinematic base clips 2️⃣ Extract last frames → key images 3️⃣ Animate‑14B → turns each image into 6–12 sec extended shots 4️⃣ Stitch → long‑form DnB video sequences Why this works: • 5B = creative short bursts • 14B = long coherent motion • Qwen = automation batch control • 2 GPUs per stage = parallel, fast, stable This is the backbone of axonis_video_engine — a local, multi‑stage AI video system designed for long‑form music visuals. More updates soon. #Wan2.2 #LocalAI #AIvideo #TextToVideo #OpenSourceAI #RTX3090
10
🔥 Running WAN 2.2 on Only 2 GPUs — Real‑World Test I’ve been testing WAN 2.2 on a 4×3090 rig, but I needed GPU 0 1 free for Qwen. So this whole experiment was done using only **GPU 2 GPU 3**. Here’s what actually works 👇 1️⃣ TI2V‑5B *does* run on 24GB cards — but only with CPU offload The VAE is too big for a single 3090. The trick is simple: • Diffusion on GPU • VAE T5 on CPU • Use system RAM as the buffer Zero CUDA OOM errors. 2️⃣ You can generate long videos (6–8 sec) reliably Using: --offload_model True --t5_cpu --ulysses_size 1 --infer_frames 32–64 It’s slow, but rock‑solid. 3️⃣ Best way to use 2 GPUs = run 2 jobs in parallel Forget multi‑GPU mode for TI2V‑5B — the VAE doesn’t split. Real‑world fastest method: • GPU 2 → Job A • GPU 3 → Job B Two videos at a time, stable. 4️⃣ You can automate 20 clips overnight I built a batch script that: • Reads prompts from a file • Runs 2 WAN jobs at a time • Queues the rest • Saves everything cleanly • Never touches GPU 0 1 Perfect for building a full DnB music video from AI‑generated clips. 5️⃣ Qwen handles the orchestration Qwen on GPU 0 1 can: • Generate prompts • Build the batch script • Manage the queue • Organize outputs • Help assemble the final video AI controlling AI. 6️⃣ Next step: full automated DnB video pipeline 20 clips → 1 music video. All generated on GPU 2 3 while Qwen stays free on GPU 0 1. This setup works — and it’s only the beginning. #Wan2.2 #LocalAI #AIvideo #TextToVideo #OpenSourceAI #RTX3090
34
After testing WAN 2.2 TI2V‑5B on a 4×3090 rig, here’s the truth: TI2V‑5B is hard‑limited to ~2 seconds. No matter what flags you use (frame_num, infer_frames), the model clamps to ~40–48 frames at 24 FPS. That’s ~1.7–2.0 seconds max. It’s not a bug — it’s the architecture. If you want 6–10 second clips, you need Animate‑14B or you need to stitch multiple TI2V‑5B clips together. TI2V‑5B = short cinematic bursts Animate‑14B = long sequences Once you know this, everything makes sense.
8
🌧️ New drop: Happy With Today Really happy with today… Can you find the best way? Can you help me another way? Dark atmospheric DnB • 172bpm • massive supersaws • haunting ethereal vocals • rolling bass
1
2
11
78,623
🔥 **Rig Update: Qwen 3.6 35B hitting 145 tokens/sec on just 2× RTX 3090s!** Just installed **Qwen 3.6 35B** across GPUs 0 and 1 with vLLM and it’s flying at **145 tokens/sec** 🔥 That’s seriously impressive speed for a 35B model on two 24 GB cards. Paired with the rest of the 4× 3090 Turbo NVLink rig (WAN 2.2 handling video gen on the other GPUs), this thing is turning into a true local AI content machine: ✅ Lightning-fast prompt writing, scripts & ideas with Qwen ✅ High-quality video clips with WAN 2.2 in parallel ✅ Audio processing, interpolation & upscaling running at the same time ✅ Full end-to-end music video pipeline — all local, all fast, zero cloud No more waiting on APIs. Full control, full speed, full privacy. If you’re running big LLMs locally on consumer GPUs, drop your benchmarks below 👇 #LocalAI #Qwen #vLLM #RTX3090 #LocalLLM #MusicVideoAI #NVLink
1
2
83
🚨 NEW DROP ALERT 🚨 “How Are You Today” just landed 🔥 172 BPM dark festival DnB Huge supersaws exploding through the night Savage rolling bass ethereal vocals floating over pure chaos How are you today… are you feeling okay?
1
3
27
146,231
🚨 **NEW DnB DROP** 🚨 172 BPM dark dystopian fire 🔥 Ultra heavy rolling bass, crushing synths, brutal drops glitchy ethereal vocals “Can feel the change of heart in me… Need you to make another start…” #DnB #IndustrialDnB #DarkDnB #Cyberpunk
2
1
7
2,342
🚨 NEW 172 BPM dark dystopian DnB heater just dropped 🔥 @axonis22 Legacy Records Star of the Week — they just reposted it 🙏 Big thanks to @_AI_DJ for the love in the thread @LifeForMusicUK More cinematic bangers locked & loaded #DnB #IndustrialDnB #DarkDnB #Cyberpunk #NeuroDnB
1
3
57
🚨 **NEW DnB DROP** 🚨 172 BPM dark dystopian fire 🔥 Ultra heavy rolling bass, crushing synths, brutal drops glitchy ethereal vocals “I’m feeling much better now… Can do this all day… It’s a secret that can stay…” Full 2-min cinematic video just dropped #DnB #IndustrialDnB #DarkDnB #Cyberpunk
1
4
2,850
🌌 New dark industrial DnB just dropped 🔥 172 BPM half-time tension, savage rolling bass, clipped industrial percussion, brutal synth stabs and ethereal doubled female vocals with glitchy chops. Hook hits hard: I know you are feeling fine Can you see me another time Things I have to do now I hope this helps me feel how Crushed, cinematic, oppressive vibes all the way. Who’s riding this one? #DnB #DrumAndBass #IndustrialDnB
3
61
🌌 New dark industrial DnB just dropped 🔥 172 BPM half-time tension, savage rolling bass, clipped industrial percussion, brutal synth stabs and ethereal doubled female vocals with glitchy chops. Hook hits hard: Ok I'm feeling good now Thinking about how Love this song right now Can you help me be loud Crushed, cinematic, oppressive vibes all the way. Who’s riding this one? #DnB #DrumAndBass #IndustrialDnB
2
48
🔥 NEW DnB BANGER JUST DROPPED 172 BPM festival destroyer: “I know what you’re waiting for… It’s just like an opening door… I can tell you want more” Massive supersaws, savage rolling neuro bass, glitchy ethereal vocals & pure anthemic chaos. Who’s ready to lose it in the drop? #DrumAndBass #DnB #FestivalVibes
1
2
77
🔥 NEW DnB BANGER JUST DROPPED 172 BPM festival destroyer: “Come feeling this great style… It’s been happening for a short while” Massive supersaws, savage rolling neuro bass, glitchy ethereal vocals & pure anthemic chaos. Who’s ready to lose it in the drop? #DrumAndBass #DnB #FestivalVibes
3
9
2,423
“Over the Wall” – 172 BPM drum & bass with massive supersaw synths, savage rolling bass and that dark industrial edge. Ethereal female vocals screaming: “Today we solved it all… you make me feel tall… can you see me not fall?” Who’s jumping the wall with me? #DrumAndBass #DnB
1
2
99
🌌 New dark industrial DnB just dropped 🔥 172 BPM half-time tension, savage rolling bass, clipped industrial percussion, brutal synth stabs and ethereal doubled female vocals with glitchy chops. Hook hits hard: Everything is alright under you I know you’re the best I can do Time with you is alright I can’t wait till tonight Crushed, cinematic, oppressive vibes all the way. Who’s riding this one? #DnB #DrumAndBass #IndustrialDnB
2
78
I'm thinking about you and this day… Feeling ok about this today… Thinking about what we could do is ok Ultra heavy 172 BPM dark dystopian DnB. Crushing bass. Brutal synths. Pure magnetic tension. New visual just dropped ↓ #DnB #DarkDnB #Cyberpunk #DrumAndBass #HeavyDnB
2
7
4,561
**🚀 My 4× RTX 3090 Turbos NVLink Rig is a Full Local Video AI Studio in 2026** **— and it’s still one of the best consumer setups you can own.** Most people think you need 4090s or H100s for serious local video generation. I’m here to tell you: **not true.** With 96 GB total VRAM NVLink, my 4× 3090 Turbo machine runs a complete parallel creative pipeline that feels like magic. ### What I’m Running Right Soon (Simultaneously): **✅ Video Generation** - **WAN 2.2 (14B MoE)** on GPUs 0 1 → Best version for 24 GB cards. Perfect motion, prompt following, and LoRA support. → 720p–1080p clips with excellent consistency. → NVLink ComfyUI MultiGPU = ~3–4× faster than single GPU. **✅ LLM Co-Pilot** - **Qwen 3.6 (vLLM)** on GPUs 2 3 → Generates song-specific prompts, scene scripts, lyric timing, style descriptions. → Stays lightning fast and responsive even while WAN is cooking clips. **✅ Audio Post-Production** Whisper, Demucs, Bark v2, MDX23 stem separation RIFE v4.6 for buttery smooth interpolation Real-ESRGAN / SUPIR for upscaling & restoration SAM2 FaceFusion for masking, VFX, lip-sync (LTX-Video audio-native when needed) ### The Killer Music Video Workflow Raw track → Qwen writes the visual script → WAN 2.2 generates the clips → RIFE smooths → ESRGAN upscales → SAM2 lip-sync finishes it. **All happening at the same time. No model swapping. No VRAM fights. No crashes.** This rig is peak “local creator” energy. No cloud bills. No waiting queues. Full creative control. If you have 4× 3090s (or similar) and NVLink — you’re sitting on one of the best video AI machines possible without jumping into datacenter territory. Who else is still rocking 3090s in 2026 and loving it? Drop your setup below 👇 #LocalAI #VideoGeneration #ComfyUI #WAN2 #3090Gang #MusicVideoAI #NVLink
2
109