Workshops, AI strategy & AI media production. We build @generaitr, the platform for AI media production you can trust. Led by @lindapierre. Behind @play_joc
Sweden
Joined April 2013
- Tweets511
- Following898
- Followers213
- Likes421
TOMLIN STUDIO retweeted
Here's a world model similar to Genie 4 that's actually open-source and available to test right now...
TOMLIN STUDIO retweeted
BREAKING: 🇸🇪 Swedish grocery giant ICA, one of Sweden's largest supermarket chains, says several of its stores have been hit by a cyberattack overnight, causing refrigerators and freezers to be remotely set to 50°C.
The incident has likely resulted in large quantities of food spoiling. Multiple stores, including ICA Kvantum in Sjöbo and Tomelilla, have reported being affected.
ICA says stores will remain closed during the morning and are expected to reopen at 9:00 a.m. Swedish time.
The company has apologized to customers and says it is working to restore normal operations.
The incident comes amid a wave of cyberattacks targeting businesses recent weeks, following similar incidents reported in France and the United States.
TOMLIN STUDIO retweeted
GENERAITR Partners can sell AI-based services on the platform and get extra credits, extra storage and visibility to buyers. Creators and small studios: apply at generaitr.com/partners/apply
#GENERAITR #AIMediaProduction #Creatives
TOMLIN STUDIO retweeted
Three new models in GENERAITR 0.5.3: Ideogram Vector 1.0 for SVG, P-Video-2-Pro-Avatar for talking avatar video, and P-Video-Upscale to take a clip you already have up to 4K.
generaitr.com/news/2-generai…
#GENERAITR
TOMLIN STUDIO retweeted
Introducing Voxtral 3: state-of-the-art Transcribe and Speech models powering Mistral’s new voice agents API. 🧵
TOMLIN STUDIO retweeted
Another example of what you can do with video segmentation using SAM3 in the MCP-native engine I'm working on - GENERAITR Engine. Colour manipulation of object in a video, object removal and object isolation etc.
TOMLIN STUDIO retweeted
Getting a new gen AI model version is always exciting, but it’s not always ”better” in every sense. Comparing LTX 2.3 vs 2.5 I find in some cases 2.5 does the job better, but sometimes it’s more a matter of taste. Which one makes you want to eat ice cream? @ltx_io
TOMLIN STUDIO retweeted
📱Playtesting. Germana 🤪 but fun with the balloons right? A bit too slow maybe and hard to get sometimes. 😅 Let us know what you think and join our Discord! Find all links in our bio. 👆#catala #catalan #llengua #languagegame
TOMLIN STUDIO retweeted
Hola a tothom! Hi everyone! Come play Joc! A fun and playful way to learn Catalan. In Alpha mode, join our Discord for support! joc.tomlinstudio.com/
TOMLIN STUDIO retweeted
GENERAITR v0.2.0 is live.
AI generation as production infrastructure. Not a creative toy.
Templates. Multi-model. EU AI Act compliant from day one.
Early Access is open. generaitr.com
TOMLIN STUDIO retweeted
People are missing this:
ComfyUI is the only tool in class positioned to ride the agent wave. Others are simply too closed off and unextensible. In a future where agents are integral to work, the artists who stuck with ComfyUI will be miles ahead of those who went elsewhere
TOMLIN STUDIO retweeted
Two massive updates for the ComfyUI ecosystem today:
1️⃣ App Mode: The power of the node graph, now behind an easy-to-use interface. Turn complex workflows into custom apps.
2️⃣ ComfyHub: A brand new home to discover, run, and share community workflows and apps instantly via URL. Try ComfyHub preview via links.comfy.org/4dke0ki
Create in App Mode. Share on ComfyHub.
Learn more here: links.comfy.org/4bAOjuz
TOMLIN STUDIO retweeted
Med generativ AI kan tomma eller neutrala rum visualiseras i olika inredningsstilar – för annonser, presentationer och idéarbete.
📄 Presentation
bit.ly/GENERAITR_Inredning_P…
🌐 Mer om GENERAITR
tomlinstudio.com/generaitr/
#ArchViz #GenerativAI #InredningAI #Visualisering #Inredning
TOMLIN STUDIO retweeted
Comfy Cloud is out of beta! Thank you to our community who helped build and test it.
Here is what this means:
- Most popular custom nodes — now in the cloud
- Pay only when your workflow runs. Never for idle time - Every major model ready instantly
- NVIDIA Blackwell RTX 6000 Pro. 96GB VRAM. In your browser.
Your pipeline. Zero setup.
Try it for free. comfy.org/cloud/pricing
TOMLIN STUDIO retweeted
⚠️ Heads up!
We’ve just discovered that new Comfy Cloud users keep receiving 400 free credits every month. And we are not trying to address it : )
Please DO VISIT Comfy Cloud if you haven't subscribed yet!
links.comfy.org/freetierx
TOMLIN STUDIO retweeted
Nano Banana 2 is now in ComfyUI.
It's smart, fast and affordable.
This model excels at text rendering + translation and real-time world knowledge. All while maintaining excellent quality.
These features will definitely unlock new workflows and use cases.
More examples ⬇️
TOMLIN STUDIO retweeted
Seedream 5.0 Lite is now live in ComfyUI!
Improved instruction following, stronger consistency and deeper world knowledge.
We tested it across various use cases. Check them out below!
ALT Refer to the design and layout style of Figure 2 and adapt the style of Figure 1 accordingly.
ALT A black horse gallops through shallow water, its reflection visible, under a cloudy sky in a dramatic black-and-white scene.
ALT A sleek, metallic robot stands on debris, illuminated by soft lighting, giving a thumbs-up gesture.
TOMLIN STUDIO retweeted
Most GenAI workflows were built for screens.
@MomentFactory needed one built for buildings.
They used ComfyUI to pre-map outputs to architectural surfaces with spatial logic enforced from day one.
As result:
✦ Concept work moved from days to hours
✦ Over 20 directions explored with 20–40 iterations each
✦ One artist operating the system, with two others focused on direction and alignment
✦ Upscaling to 18K in ~20 minutes post-approval
This is when generative AI stopped being a black box and started behaving like controllable, spatially-aware material.
Full case study here -> bit.ly/4r06X3A