Pinned Tweet
Our founder never filmed this.
HeyGen's Avatar 6 is now live on Wireflow. One photo and a voice track in, a talking video out.
→ Lip sync, gestures and expression follow the audio
→ 1080p or 2K, up to 60 seconds
→ Direct the performance with a plain-English motion prompt
→ Wire any voice node into the audio, or your own recording
→ 15 credits a second at 1080p, charged on the real length
Would you have noticed?
Seedance 2.5 in 4K is live on Wireflow.
→ 3840x2160, 10-bit, straight from the model
→ Same node, pick 4K in Resolution
→ Works with reference video, so an edit keeps the original cuts and sound
→ One photo in, and that's you in the shot
This clip is one take.
Try it: wireflow.ai/models/seedance-…
ByteDance's Seedream 5.5 and Seedance 2.5 Flash are now live on Wireflow.
→ Edit the same image round after round. What you don't touch stays put
→ Native transparent PNGs, soft steam included
→ Sharper small text, English and Japanese in one frame
→ More natural skin, light and materials
→ Seedance 2.5 Flash animates any frame for about 35% less per second
wireflow.ai/models/seedream-…
What would you edit first?
Every model is on the Wireflow API too. Same nodes, one key.
Seedream 5.5 (text to image): wireflow.ai/models/seedream-…
Seedream 5.5 Edit: wireflow.ai/models/seedream-…
Seedance 2.5 Flash: wireflow.ai/models/seedance-…
All models: wireflow.ai/models
API docs: wireflow.ai/docs/api
49
Kling 4.0 Flash is now live on Wireflow.
→ Set Model to Flash on the Kling 4.0 card
→ 5 second 720p clip: 54 credits, vs 91 on Kling 4.0
→ 3 to 20 seconds from a prompt, a start frame or up to 10 reference images
→ Edits clips up to 20 seconds
wireflow.ai/models/kling-4-0
What would you draft first at 41% fewer credits?
No video models were used in this scene.
Our agent built the whole room in Blender code: the rain on the window, the warm lamp, the light bouncing off the walls, the slow push-in.
On a cloud GPU that's about 4 cents a clip. Five seconds from a video model runs about $1.80.
We're putting this behind an API: describe a scene, get the shot back.
What would you build first?
Google's Gemini Omni 1.2 Flash is now live on Wireflow.
Every shot in this video was made with it:
→ 15 second scenes with lip-synced dialogue
→ edit any shot with one sentence
→ up to 6 reference images to keep characters consistent
→ first and last frame control
→ up to 4K, or draft at 360p for about 2¢ a second
Try it: wireflow.ai/models/gemini-om…
What would you make with it?
Meet Gemini Omni 1.2 Flash, our updated video generation model from @GoogleDeepMind 🎬
Get stronger consistency, more creative control, and faster, more cost-effective video creation at scale:
⚡ Fast & 30% lower cost: Draft at 360p or 720p ($0.07/s) and upscale to 1080p or 4K
⏱️ Longer clips: Generate and edit videos up to 15s, or pick any exact length from 3s to 15s
💬 Edit in conversation: Swap backgrounds, subjects, or lighting turn by turn without starting over from scratch
🗣️ More natural speech: Create fluid, multi-speaker dialogue with clearer lip-sync
🎬 More controllable shots: Direct continuous camera moves with fewer jump cuts
See these updates in action ↓
Try Gemini Omni 1.2 Flash on Wireflow:
Text to video: wireflow.ai/models/gemini-om…
Image to video (first + last frame): wireflow.ai/docs/nodes/video…
Reference images to video: wireflow.ai/docs/nodes/video…
Video edit: wireflow.ai/docs/nodes/video…
44
GPT Image 2.6 lets you draw on any photo and it makes it real.
Everyone's demoing lamps and cats. We gave this guy a Lamborghini, a gold chain and two friends.
Live on Wireflow. What would you draw on him?
Try it here:
Sunburst Text-to-Image
wireflow.ai/models/gpt-image…
Sunburst Edit
wireflow.ai/models/gpt-image…
Flare Text-to-Image
wireflow.ai/models/gpt-image…
Flare Edit
wireflow.ai/models/gpt-image…
1
62
Who’s next?
YC startups ship every day and launch in silence.
So I'm making one launch video a day for a startup that deserves it.
Day 1: @AsideAI, the browser built to do real work for you. cc @hyojun_at
Reply with yours and you might be next.
1
4
168
Kling 4.0 is now live on Wireflow.
The latest model from @Kling_ai brings:
• Up to 30 seconds of video with sound
• Up to 10 reference images to keep characters and props consistent
• Start and end frame control
• 720p or 1080p
Try Kling 4.0 on Wireflow today. Text, image and reference to video in one node:
wireflow.ai/models/kling-4-0
1
100
Our founder remade pump.fun's viral ad with AI in one afternoon.
Every prompt is in here, including a free-plan version you can run today.
155
Wireflow AI retweeted
I'm making 5 AI videos a day with Claude + Wireflow.
Here's the full workflow, what it costs, and what's not working yet.
Reply FLOW and I'll DM you the Claude skill and Wireflow board.
Nano Banana 2.1 is live in Wireflow.
Every image in this video came off one board:
a soda can, a Swiss poster, anime, a glass horse, the same cafe in four looks, and a whole snowy street as one 8:1 image
Wireflow AI retweeted
In SF for @Techweek_ this week.
We remade Higgsfield's launch ad in Wireflow for under $100 in raw generation costs. Film and breakdown below.
Building or investing in creative AI? Let's grab coffee and swap demos. I'm here through Sunday.
#SFTechWeek







