Heinrich Lab

i'm just a figment of your imagination

[ComfyUI @ComfyUI]

Count down starts 🥁...

And no, it's not fundraising announcement this time.

[Heinrich Lab @GeekDynamics]

@NVIDIAGeForce #RTXON FTW on every graphics tasks, unbelivable!

[NVIDIA GeForce @NVIDIAGeForce]

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: https://t.co/45T3R732hf

[Rebel AI @realrebelai]

P-JiT

a 2B parameter model with quite a punch!

testing is going decently well. theres of course some weaknesses but that it to be expected from such a small model.

bf16 is the only format i coded for so far

nodes:
https://t.co/csjX9a8sO9

comfy models:
https://t.co/PKBvnuSSD0

[Rebel AI @realrebelai]

👀👀👀👀👀

[Heinrich Lab @GeekDynamics]

@realrebelai I agree, all our appreciation to all the teams that make this models, keep the good work guys, you are awesome

[Heinrich Lab @GeekDynamics]

Angels #AIart #AI

[ComfyUI @ComfyUI]

MOSS-Image is now supported in ComfyUI

@OpenMOSS dropped an open-weight image model that has blown up across the community. It’s a 5B model that renders legible text, accepts structure layout prompts and has a high bar for aesthetics.

The community has already been cooking up finetunes and LoRAs while the Comfy team has been working to support the model to run seamlessly on any consumer hardware.

This model is a must try - check it out.

[Krea @krea_ai]

today we open the beta for Krea 3, a new frontier for image editing.

- end-to-end 2k edits in under 8s.
- matches Nano Banana Pro or GPT Image 2.5 quality.
- bounding box control and precise multi-turn edits.

learn and get access 👇

[Rebel AI @realrebelai]

dude.... this model is absolutely insane. @krea_ai

#krea3

[titus @TitusTeatus]

krea 3 really is like nothing else

nano banana pro / chatgpt 2 image quality in <7s at 2K pixels

coming this thursday @krea_ai

[Rebel AI @realrebelai]

Who wants Krea 3 early access?

Comment below, i have 4 more spots available.

Ill select them at random with Muse to keep it fair! 👀🫡

[ComfyUI @ComfyUI]

Clearing the canvas! 👀

[Krea @krea_ai]

something is coming.

who wants early access? 👇

[toyxyz @toyxyz3]

https://t.co/BG94UDlB0c

[Isra @Israfilv2]

what the f*ck, new Uncensored Qwen-Image-2.1, actually abliterated this time

and you can run locally in your laptop (Q4_K_M is 4.68 GB only)

- the fix is in the text encoder, not the image weights
- refusals drop from 100 out of 100 to 5
- it does not get dumber on normal prompts
- edit with up to 10 reference images
- native transparency (stickers, cutouts, no extra mask step)
- ComfyUI + city96 GGUF loader

https://t.co/OQKQiYY7DK

[Unsloth AI @UnslothAI]

Qwen-Image-2.1 can now run locally on 12GB VRAM with Unsloth GGUFs! 🖼️

The 7B model performs on par with Nano Banana 2.0.

For higher quality, you can also run Dynamic FP8 on just 6GB of VRAM via offloading.

GGUF: https://t.co/gRDt6cJWfe
Guide: https://t.co/Xijw16FKqd

[MiniMax (official) @MiniMax_AI]

Music 3 is open too!! 🙌 Already live locally on @ComfyUI

"We will keep open until AGI arrives." 💙

Cloud coming soon.

[MiniMax (official) @MiniMax_AI]

Maestro v1.5.5 with MiniMax H3 is out! 🩵

The community got H3 running on hardware we never tested - from a gaming GPU to MacBooks running fully offline - and built tooling we didn't plan for within 48 hours.

We're genuinely glad we opened it up. <3

[ComfyUI @ComfyUI]

MiniMax H3 open weights are out, with the nodes already in ComfyUI.

One Blender blockout, run against Seedance 2.0 at a fraction of the cost per generation, leaving more room for experimentation and iteration.

To try this workflow, link below 👇