With COSMOS3 EDGE 4B now released, I'm curious about ANIMA's future direction
Beginner question here. Since I'm not entirely familiar with how COSMOS actually works under the hood, I'd like to ask a few things:
- I noticed that COSMOS3 EDGE 4B doesn't have text-to-image capabilities at all β it's purely a reasoning model. Does this perhaps mean that the community's expectations for COSMOS3 have been completely dashed?
2.Will the next iteration of ANIMA continue to focus on aesthetic refinement built on top of the existing COSMOS2 foundation, or will it seek opportunities on other base models?οΌThis might mean that the existing ANIMA ecosystem will be disrupted and rebuilt from scratch.οΌ
3.Will future ANIMA releases still maintain relatively good compatibility with limited VRAM (e.g., 6GB, 8GB)?
Thank you for providing such an amazing model for us.
From my reading of the description, it seems to have image generation capabilities.
However, the bigger issue is that after stripping away the cumbersome parts for comparison, although the overall generative part is smaller than Anima, there is not much difference in essence because it simply offloads the load to the inference side.
Furthermore, Wan2.2's VAE is actually quite lacking in visual reconstruction and trainability.
It falls short compared to modern VAEs like Flux 2 VAE or continuously improved series like Qwen Image 2.0 VAE.
Its reconstruction quality is also inferior to the Qwen Image VAE currently used by Anima, which is on par with Flux 1 VAE.
Wan2.2's VAE is undoubtedly a tier below, and it is arguably even worse than Wan2.1's VAE.
At the same time, looking at the situation, the model seems to lack high-resolution images, so a lot will need to be supplemented during subsequent training and fine-tuning.
On top of that, since the generation component packs in too many things, its effective capacity might not be very large.
Cosmos3 Edge may not be a suitable choice for a next-generation model.
What about that new Microsoft model? How flexible is it with full scale finetunes? It really is far from SOTA, but seems like a upgrade from Cosmos and it's small and has a good license
Still I think native MMDiT can be an upgrade for consumer-GPU developers since various image-to-image methods require multimodal attention architecture.
I don't work with CircleStone Labs but I can definitely talk about these:
- I noticed that COSMOS3 EDGE 4B doesn't have text-to-image capabilities at all β it's purely a reasoning model. Does this perhaps mean that the community's expectations for COSMOS3 have been completely dashed?
It does, and in fact it's sort of an "omni-modal" model so it supports text/image/video/action inputs and outputting text/image/video/action. Sadly, they stripped audio capabilities from Edge 4B, so you'd have to use Nano 16B or Super 64B for audio inputs/outputs. The models are just 50% Qwen3 2B, 8B, or 32B LLM (the "Reasoner" tower), and 50% DiT (the "Generator" tower).
The obvious issue is that Cosmos 3 is trained to be robotics-first, and very VERY few people, not even most ML researchers, are able to work with such a broadly capable architecture effectively. While the pre-trainin is there, it will be a huge task to post-train tens of millions of images and videos including 15 million in the current booru dataset. But I think it could (theoretically) be genuinely incredible.
2.Will the next iteration of ANIMA continue to focus on aesthetic refinement built on top of the existing COSMOS2 foundation, or will it seek opportunities on other base models?
There are actually Cosmos-Predict2-0.6B-Text2Image and Cosmos-Predict2-14B-Text2Image, alongside the 2B that the current Anima 1.0 was trained on. I could see those being the easiest targets for additional Anima models, but they are over a year old as of now. Another potential base is Krea 2 Turbo (which is CFG distilled and only requires 8 steps), however it is 12B so it would take a lot of VRAM (would run about the same speed as Flux.1).
I genuinely don't understand what the hub-bub about "HEY GUYS LET'S BURN TENS OF THOUSANDS OF DOLLARS DOING THE SAME TRAINING ON NEW MODEL" expecting a different, much better, result.
You could instead spend a few hundred dollars giving someone a job to implement Normalized Attention Guidance for this architecture, enjoy the various high-diversity low-stepcount distillations, mayhaps even invest into implementing both of these things into krita-ai-diffusion as that is the only competent image-diffusion + image-editor mix I've seen.
Then you'd have a great compositional model, which prints images very quickly even on piddly hardware, and has working positive and negative prompting that doesn't break with controlnets for further pipeline expansions (e.g. using OPii Rig03 in Blender)
but that's like, just my opinion, man
and that requires like, giving someone with programming skills a job, interacting with people...
This model already works shockingly good, with a few toolchain expansions, it would work fantastic as the bedrock of low-hardware 2D art production - why throw all that away?