GPT Image 2.6 is on Montagea, in two versions: Sunburst and Flare.
It now makes files, not just pictures:
→ SVG: a real vector that scales to any size and opens in your design tools
→ GIF: a looping animation of up to 16 frames that can bring your reference images to life
We made a whole pack of animated Gigi stickers from one reference picture. SVGs are drawn from your prompt alone; GIFs can start from your references.
Up to 16 reference images, up to 4 images a request, priced on what each image actually uses. On paid plans: montagea.com/gpt-image-2-6-s…
Images, upgraded—introducing ChatGPT Images 2.6.
Now with GIFs and reference images.
Plus, two new models are coming to the API with 50% faster image generation.
1
90
Senior Year · September to May.
Two characters, one reference photo each, five shots, and their faces never change. Made with Gemini Omni 1.2 on Montagea.
#aishortfilm #geminiomni #aivideo
"Best night." One school year in 37 seconds, made with Gemini Omni 1.2.
#aishortfilm #aivideo
Whether you're directing a cinematic thriller (or just cooking a pizza), sometimes you need a little more time to get to the good part.
Well now with Omni 1.2 Flash rolling out today in Google Flow, you’re in luck!
Here’s what’s new:
→ Quality improvements: For all users, experience stronger visual consistency, fewer jump cuts, better reference adherence, and more natural speech.
→ Longer continuous shots: Up to 10s for all users, with 11 to 15s available for Google AI subscribers.
→ Extend, also now with ingredients: Lengthen clips and steer what happens next using reference images, available for Google AI subscribers.
→ Per-second pricing: With Omni 1.2 Flash, we’re introducing per-second pricing which means you’ll be charged for the duration of the content you generate, edit, extend, or upscale.
Rolling out today, go create at flow.google.com 🍕
1
37
Gemini Omni 1.2 Flash is live on Montagea.
→ Any length from 3 to 15 seconds
→ 360p up to 4K
→ Up to 6 reference images, so your characters keep their faces shot to shot
→ Native sound: it speaks the lines you write
→ Edit or extend a clip you already have
1.1 rendered 4, 6, 8 or 10 seconds. 1.2 takes any whole second from 3 to 15, and you pay for the seconds you render.
Same faces in every shot: our short film used one portrait for all five shots. For two characters, give each one a portrait (up to 3 per character).
Make it in Studio, or just ask Gigi for the shot: montagea.com/gemini-omni-1-2…
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 ↓
1
80
Same prompts. Two different takes.
Pika H3 Flex vs FastH3-Omni, side by side 👇
Which one would you pick for your next video?
@pika_labs @haoailab
montagea.com/minimax-h3
1
2
122
Pika H3 Flex and FastH3-Omni are both live on Montagea! Try them with free credits, or use them through our API or MCP.
Shoutout to @pika_labs and @haoailab 🙌
montagea.com/minimax-h3
(1/6) @pika_labs open-sourced @MiniMax_AI H3 Flex late last week. Today it's in FastVideo, and it's fast.
Up to 7x faster than the official open-source inference code
5 s of 480p video + audio in 5.8 s on one @NVIDIAAI GB200
Open weights + the full training recipe:
FastVideo: haoailab.com/FastVideo/cookb…
Weights: huggingface.co/FastVideo/Pik…
Blog: haoailab.com/blogs/pika-h3-f…
We’re now serving FastH3 Omni 8-Step V1 through the Montagea API.
Bring your image, video and audio references. We handle the GPUs.
Build with it 😃: montagea.com/docs/api
As promised, FastVideo open-sources @MiniMax_AI FastH3 Omni, training code included! 🚀
- Real-time gen @ 12x faster on NVIDIA Blackwell
- NVFP4/FP8 for Spark + RTX!
- ComfyUI day-0
Collab with @NVIDIAAI , Nuva Lab @nuvalab and Reactor @reactorworld
Open source must win! ♥️
1
2
24
Introducing AI Avatar on Montagea.
Create an AI version of you—with your look, voice and personality.
Fans can chat privately and request photos, videos and voice messages. You earn from paid media.
Create yours on Montagea.
34
🚀 Qwen3.8-Flash "Uncensored" is now LIVE on Montagea!
🔥 Fewer restrictions. More freedom. Endless possibilities.
✨ Try it for FREE at montagea.com/qwen-uncensored…
#Qwen #UncensoredAI #Montagea #AI
⚡Meet Qwen3.8-Flash, a multimodal MoE and an early preview of the Qwen4 architecture, now open-weight!
The production version Qwen3.8-Flash will be available soon via QwenCloud API at just $ 0.16/1M input tokens and $ 0.47/1M output tokens.
125B parameters + 51B N-gram embeddings, with just 6B activated per token. Unmatched cost-efficiency.
What's new: 🥳
- Next architecture: GDN + QSA hybrid attention, Gated Residual, N-gram Embedding & Muon optimizer, serving as a precursor to the architecture used in Qwen4.
- Dramatically lower training and inference costs: trained at just 1/9 the cost of Qwen3.7-Plus, while outperforming it across the board with especially strong gains in coding and office tasks.
- Strong performance: scoring 58.7 on DeepSWE 1.1, 62.5 on SWE-bench Pro, 73.9 on CoWorkBench, 84.5 on AndroidWorld, and 95.7 on MathVision (with CI).
- 262K native context, extensible to 1M with YaRN.
We’re also releasing the weights for Qwen3.8-Flash-Next, giving the community an early look at the new architecture we’re exploring for Qwen4.🚀
We can't wait to see what you build with Qwen3.8-Flash!👀👇
- Blog: qwen.ai/blog?id=qwen3.8-flas…
- Technical Report: github.com/QwenLM/Qwen3.8-Fl…
- Hugging Face: huggingface.co/Qwen/Qwen3.8-…
- ModelScope: modelscope.cn/models/Qwen/Qw…
153
🚀 Qwen-Image-2.1-Turbo is now LIVE on Montagea!
Create stunning AI images faster and easier than ever.
✨ Try it for FREE at montagea.com/qwen-image-2-1
#Qwen #AIImage #Montagea #GenerativeAI
🚀 Meet Qwen-Image-2.1-Turbo — create and edit images in just 8 denoising steps! Open weights now available!
Built on Qwen-Image-2.1, Turbo is an accelerated checkpoint on the same 7B visual generation architecture.
Fewer steps does not mean lower quality: it still generates strong 2K images from text, and supports continued creation through natural-language edits, from adding accessories to changing a scene.
Start directly with Diffusers: load QwenImage21Pipeline and the checkpoint’s recommended 8-step sampling schedule is ready to go.
🌐 Prefer an API? Qwen-Image-2.1 Pro and Turbo APIs are now officially live. Choose a hosted API for your application, or use the Turbo weights in your own workflow.
🤖 ModelScope:
modelscope.cn/models/Qwen/Qw…
🤗 Hugging Face:
huggingface.co/Qwen/Qwen-Ima…
🔗 Pro API:
modelstudio.console.alibabac…
🔗 Turbo API:
modelstudio.console.alibabac…
What will you create with 8 steps? Share your results with us!
1
191
No crew. No studio. Just tell Gigi what you're selling — she writes the script, plans the shots, and creates the video, voiceover and music. Start free on Montagea.
23
Still paying for stock footage and photo shoots? Describe the ad you want to Gigi, your AI creative director, and get the script, shots, voiceover and music in one chat.
16
Qwen Image 2.1 is now live on Montagea 🚀
Generate stunning images with the latest Qwen model — and try it for free today.
montagea.com
1
122
MiniMax is now FREE on Montagea. 🎬
Generate AI videos with MiniMax at no cost — just create, experiment, and have fun.
Try it on Montagea today.
2
62








