Generative AI specialist /Motion Graph Working on AI first projects, XR games, documentaries and films. ComfyUI, After Effects, Ableton, Claude Code.
Finland
Joined March 2016
- Tweets9.1K
- Following695
- Followers1K
- Likes8.9K
Heba AI retweeted
We're giving away a Hogwarts Legacy custom wrapped NVIDIA GeForce RTX 5090 to celebrate its official release with DLSS 5 🪄
To enter:
🟢 Share this post
🟢 Comment #RTXON
Terms and Conditions: nvidia.com/en-us/geforce/con…
Heba AI retweeted
Defined roles and “agent” archetypes are so 2024 lol
We are definitely exploring “bot” like systems, specifically meta threads for commanding your threads/agents/envs, but it will not be a defined role system because those are artifacts of a time where models were much dumber.
Heba AI retweeted
@higgsfield_ai sent us a cease and desist last night, asking us to shut down our Open Source Higgsfield challenge.
Our read on why they sent it. When the apps people pay for can be rebuilt in the open in two weeks, that’s an uncomfortable thing for a closed platform to watch.
So here’s us reiterating our promise to every builder in the challenge and community, and we’re keeping it:
• The challenge stays open
• Final submissions close tomorrow, Oct 30
• Winners are announced Nov 6, with prizes paid as promised
You showed up for each other. We’re showing up for you.
If we win, we all win!
Comfy out 🫡
Last night, @higgsfield sent @ComfyUI a cease and desist (attached)
They want the Open Source Higgsfield challenge taken down within 48 hours.
Their argument is that our use of the Higgsfield name and that using their CEO's likeness is an infringement violation (man, the irony). Claiming that it makes the event look like Higgsfield is associated with it.
This couldn't be farther from the truth, which is that Higgsfield made a promise to open source its product and never did.
For the past two weeks, builders have been recreating popular closed apps as open workflows anyone can run.
So we asked our community to deliver where Higgsfield failed: apps in the open, built by the community, for the community. We've made it clear that the challenge is organized by ComfyUI and not affiliated with or endorsed by Higgsfield.
When we started Comfy, we made the community a promise. Our product stays open, free, and yours. We’ve kept it every day since, and one letter isn’t going to change that.
The challenge stays up. Comfy and open source will win!
Heba AI retweeted
Free Friday: GForce’s superb Axxess instrument is free through the end of November.
cdm.link/gforce-freebies/
Heba AI retweeted
A Qwen Image 2.1 restoration lora. See example image, its self-explanatory.
Once again, another lora that tackles Qwen Image 2.1's consistent need to pollute the image with details.
Thanks to @Zanzibased for the baking the lora.
huggingface.co/ausboss/Qwen-…
Heba AI retweeted
Ostris AI Toolkit now supports training LoRAs for @MiniMax_AI MiniMax H3. Only T2V and I2V for now. I will be adding reference, more features, and optimizations over the next few days. This one uses Comfy quantized weights, read the model notes for more info.
Heba AI retweeted
Kimi uses roughly 2x the tokens per request that 5.6 uses. Fable uses 50% more beyond that.
Token pricing doesn’t really matter anymore.
Heba AI retweeted
‼️ BREAKING: A hacker breached AI music company Suno using the Shai-Hulud worm and released source code showing how its training set was built:
- 113,879 hours of YouTube Music
- 62,117 hours of Pond5
- 12,287 hours of Deezer
- plus Genius lyrics and a plan to download roughly 1 million hours of podcasts
The same intrusion reached customer emails, phone numbers, and Stripe payment data for what the hacker says is hundreds of thousands of users.
Suno dates the incident to November 2025, calls it limited, and says individual notifications were not warranted. Customers are surprised to not have been informed about the breach.
Heba AI retweeted
George Lucas says AI makes it "much easier for us to make movies" and "there’s nothing you can do about it. That’s progress, it’s the future.”
“Artificial intelligence means it’s much easier for us to make movies. It’s very much like sitting here saying, ‘Well, I believe the horse and the buggy is really where it’s at. These cars, they break down, they need gas, there’s all kinds of problems with them and pretty soon they’ll be making them into tanks, and then they’ll be killing people. It’s terrible.’ There’s nothing you can do about it. That’s progress, it’s the future.” (via A Rabbit's Foot)
variety.com/2026/film/news/g…
Heba AI retweeted
⏰ Local MCP server for ComfyUI.
Inspect workflows, edit graphs, queue generations, and manage models from MCP-compatible agents.
This is a very powerful MCP server exposing virtually everything about comfy to the agent! Forming a bridge that allows your agent access to both the front end and backend systems. of ComfyUI
What it can do:
• Inspect the current open workflow
• Read node titles, inputs, outputs, links, and positions
• Edit graphs and reconnect nodes
• Compact and organize messy workflows
• Queue generations from an agent
• Discover local models, LoRAs, VAEs, and checkpoints
• Debug missing models or broken node links
• Take screenshots of the live ComfyUI canvas
• Work through the browser bridge or ComfyUI API
The agent is even able to code node packs for you, fully manage the running instance of comfy, as well as Verify with screenshot integration of graph state.
Iv been sitting on this one for a long while, its time to see some crazy stuff you guys do with it!
Heba AI retweeted
LTX-2.3 Foley LoRA
- It adds Foley that actually matches the action on screen.
- stops the model from defaulting to background scores when you just want real-world noise.
- makes generations feel like actual raw footage
huggingface.co/FuzzPuppy/LTX…
Heba AI retweeted
Introducing Nano Banana 2 Lite 🍌 and Gemini Omni Flash 🔮, our new generative media models in the Gemini API and AI Studio!
Nano Banana 2 Lite is extremely fast (<4s image) & cheap ($0.034 / 1K image).
Omni Flash is SOTA at video editing at $0.10 / sec, same as Veo 3.1 Fast!
Heba AI retweeted
Ostris AI Toolkit has day 0 support for training LoRAs on Krea 2. The model has beautiful aesthetics and finetunes very well. 🧵
