tell us about your 5.2 and 6.1 usage! people say this but overall the usage on these models is quite low right now
GENERATIVE AI
-
Higgsfield Launches Soul Cinema Cinematic Image Model
By
–
Higgsfield just rolled out Soul Cinema, its most cinematic image model yet ✋🧩🤚
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 18 mars 2026
After strong feedback from the preview, it’s now fully available; bringing more realistic, film-like visuals.
New Pro+ users can get up to 10,000 free generations to try it out.
Works best when… pic.twitter.com/WSZ2P4aclZHiggsfield just rolled out Soul Cinema, its most cinematic image model yet After strong feedback from the preview, it’s now fully available; bringing more realistic, film-like visuals. New Pro+ users can get up to 10,000 free generations to try it out. Works best when
-
Whale Image Generation: Prompt and Settings Details
By
–
wow that whale one is beautiful, what kind of prompt / settings did u use to make that?
-
Optimizing Anime Generation: Raw Mode and Moodboard Parameters
By
–
it's very possible that –raw and moodboard is necessary for good anime results right now, is there anything else you think we could / should improve? <3
-
Using V7 Image Styles as References in V8
By
–
if there's a specific style you like from v7 you can try bringing it into v8 by using the old v7 image as a style reference. if you can tell us the prompt we can look at it with our team too! <3
-
Top priorities for AI improvement right now
By
–
what do you think are the top things to improve right now?
-
Image Generation Model Improvements: Better Hands, Body Rendering
By
–
hands and body are quite a bit better! we can render thousands of images with both versions and the difference is obvious. our moderation is tuned differently for each version but if you see it behaving in obviously wrong ways please let us know so we can improve it. thanks! <3
-
Paid Community Funds Server Infrastructure for AI Model Training
By
–
we have money from a paid community that we put back into buying servers for running models and training models, this feels honest and we're happy with it
-
Mamba-3 Release: Linear Models for Hybrid Architectures
By
–
Oh wow, Mamba-3 is here! For me, the most interesting use case of Mamba and Mamba-likes are the recent transformer attention hybrid architectures (Qwen3.5, Kimi Linear, etc.) Would be interesting to swap Gated DeltaNet with Mamba-3 (which now also has RoPE) in next gen hybrids. Albert Gu (@_albertgu) The newest model in the Mamba series is finally here 🐍 Hybrid models have become increasingly popular, raising the importance of designing the next generation of linear models. We've introduced several SSM-centric ideas to significantly increase Mamba-2's modeling capabilities without compromising on speed. The resulting Mamba-3 model has noticeable performance gains over the most popular previous linear models (such as Mamba-2 and Gated DeltaNet) at all sizes. This is the first Mamba that was student led: all credit to @aakash_lahoti @kevinyli_ @_berlinchen @caitWW9, and of course @tri_dao! — https://nitter.net/_albertgu/status/2033948415139451045#m