
CEO @wavespeed_ai. Building the best AI image & video generation platform in the world.
Joined August 2020
- Tweets200
- Following90
- Followers492
- Likes226
Wavespeed for GPU (Photo AI + Interior AI)
Cloudflare for R2 storage and domain renewal
xAI for LLM AI API for all my sites
Backblaze for backups
Hetzner for VPS
Scrapingbee for scraping (mostly for Hotelist)
Google Cloud (also for Hotelist)
NameCheap (for like 4 domains left that I can't transfer into CF)
Replying to @levelsio
‘I'm down to just about 10 companies I pay now’
Doing the same down to about 20 tho. Less is more.
Cheng Zeyi retweeted
Meet WaveSpeed CLI ⚡️
Access every model on WaveSpeedAI right from your terminal.
🎬 Run image, video, audio, and 3D models
⚡ Generate with a single command
🤖 Works great with Claude Code, Cursor, Codex, and AI agents
🛠️ Live model docs and parameter help
📦 Reusable aliases for faster workflows
📄 JSON outputs for scripting and automation
🔓 Open-source and built for developers
No dashboards. No extra clicks. Just build.
Install now
npm install -g @ wavespeed/cli
Cheng Zeyi retweeted
From one idea to a full K-pop style music video
Today's creators no longer need:
🎥 Large production teams
💃 Professional dancers
💡 Studio setups
💸 Massive budgets
This entire video was created with WaveSpeed AI Generator.
The future of content creation belongs to creators who know how to combine AI tools into powerful workflows.
Cheng Zeyi retweeted
This combo is kind of unfair
GPT Image 2 for storyboard
Seedance 2.0 for execution
From idea → storyboard → full sequence
All smooth
10% OFF on Seedance 2 is still live
Try it on WaveSpeedAI 👇
Cheng Zeyi retweeted
🤯OpenAI gpt-image-2 is setting a new bar for AI-generated visuals!
Better text rendering. Stronger layouts. More polished results.⚡️⚡️⚡️
If you’re building campaigns, social creatives, or brand assets with AI, take a close look at these outputs and give it a try.🤩
Cheng Zeyi retweeted
SEEDANCE 2.0📽️
1080P direct output
Cinematic-level visuals
Complete creative freedom
Doesn't look like AI anymore
Let your imagination run wild🔥😉
Cheng Zeyi retweeted
We're past the "AI looks fake" phase.
WaveSpeed takes AI video to the next level —
all AI media models in one platform.
Now it's simple: can you think of it?
RT + Like for free credits 🎬
Cheng Zeyi retweeted
Nano Banana 2 — 20% OFF (1 Week Only) 🍌
⚡ Better performance
💰 Lower price
🎁 Extra GIVEAWAY: $10 Credits × 10 winners
📷 Follow + RT + Comment to enter
Limited-Time: Feb.28- Mar.6 (UTC+8)
Don't miss it 👇
Cheng Zeyi retweeted
Elevate your storytelling with WAN 2.6 Pro Image-to-Video.
Our premium image-to-video model is now live, featuring:
✅ Multi-shot consistency
✅ 5–15s cinematic clips
✅ Stunning 1080p–4K output
The perfect balance between visual anchors and prompt-driven motion.
Cheng Zeyi retweeted
WaveSpeedAI Desktop is here.
Built for people who run models daily:
• Multi-tab workspace — run multiple models side by side
• Batch processing — generate 2–16 variations at once
• Templates — save setups you like and reuse them
• Full LoRA support
• Local history & asset management
Less friction, more creating.
Check it out.
Cheng Zeyi retweeted
🚀VIDU Q3 IS LIVE on WaveSpeedAI
🔥 50% OFF for ALL users (Feb 1–7 UTC+8)
- Up to 16s video generation WITH audio
- Dialogue & content-friendly
- Affordable & cost-effective pricing
🎁 GIVEAWAY: $10 credits × 10 winners
👉Follow + RT + Comment to enter
Create more. Pay less. ⚡️
Cheng Zeyi retweeted
Tired of regenerating the same prompt 50 times, hoping for THE ONE? 🎰
FIBO changes everything.
Excited to partner with @bria_ai_ and bring FIBO edit to WaveSpeed — the open source production grade model that actually listens.
Change the lighting? ✅ Only lighting changes.
Adjust camera angle? ✅ Everything else stays.
No cascade. No drift. No luck needed.
Cheng Zeyi retweeted
🚨 New image editing models are live — built for precision & control 🎯🎨
⚡ FLUX.2 Klein 4B Edit
Fast, cost-efficient edits from natural language
up to 4 reference images
🎨 FLUX.2 Klein 9B Edit
9B params for ultra-high-quality edits,
precise control & multi-reference style transfer
Cheng Zeyi retweeted
Get started with Wan 2.6 Image-to-Video Flash
wavespeed.ai/models/alibaba/…
Cheng Zeyi retweeted
🚀 New Drop: Wan 2.6 Image-to-Video Flash
Meet Wan 2.6 Image-to-Video Flash — #alibaba's fast image-to-video generation model.
🖼️ Upload an image
🎬 Describe the motion
⏱️ Generate videos up to 15s
🔊 Optional synchronized audio
Turn a single image into dynamic video — fast and easy. 🔥
Cheng Zeyi retweeted
🚀 FLUX.2 Klein just dropped on WaveSpeedAI
⚡️ Text-to-image, tuned for speed + quality.
⚡ 4B : blazing-fast, efficient text-to-image
🎯 9B : sharper realism + crisper text
🖼️ JPEG / PNG / WebP
From idea → image, faster than ever.
Cheng Zeyi retweeted
🚀 Meet GLM-Image Edit —
Z-AI's powerful image transformation model.
✨ Key features:
📝 Edit images with natural language prompts
📸 Upload up to 4 reference images
🧠 Preserve key elements & identity
🎯 Apply precise, controllable modifications
🖼️ High-quality, faithful image reimagining
Describe the change.
GLM-Image Edit does the rest. 🔥
Cheng Zeyi retweeted
🔥 LTX-2 Control just dropped on WaveSpeedAI
Turn any video into something new without breaking motion.
🎥 Control with pose / depth / edges
🧠 Powered by a 19B DiT backbone
🔁 Motion structure preserved, frame to frame 🔊 Audio, your way: keep it / regenerate it / mute it
Video-to-video transformation with real control.
Cheng Zeyi retweeted
🔥 #Seedance 1.5 Pro just dropped on WaveSpeedAI
Audio-video native.
Perfect lip-sync.
Expressive motion.
Multilingual, multi-speaker, production-ready 🎬⚡
Build with it now.
















