Turns out, it's (mostly) great. especially multi people Anatomy. I use it a lot now.
I'm not talking about NSFW, that has to come from the community as usual. At least, If that means simply nakedness. But because of the below it is quite good for example with the anatomy and geometry of kinkyness* without messing stuff (Arms, legs hands) up as much as others. It is flatout better at this stuff than Flux2 Klein. Even Flux.2 dev. Maybe even Qwen Image.
i mention this below but after testing the "1k hotfix" turbo models i wanna make it more visible: Using the (int8) base model + the turbo lora at 1.0, has vastly superior results (especially in creativity and variety) over using the turbo model.
with roughly the same speed. If you can, or if you are underwhelmed with turbo results, prefer that! Whatever they hotfixed, it has NOT changed that. Also that precise editing is not it's storng suite in either config.
Anyway, anatomy, complex scenes...:
So i'm talking arms, hands, legs, people in close, complicated, multi people interactions and so on. This model, coming completely out of the blue, it is VERY good at anatomy. and geometry in general.
Boogu Image (edit) seems to be better at geometry and spatial understanding even with many moving parts (people) in an image/prompt than just about anything else (free).
It's good with complex (or simple) prompts, without any Json or rewriting BS needed, even simple hand written prompts (in 2026!) It just works! (in generation, actual editing is a bit weaker). So Boogu has sneakily slowly become my most used image gen model. for all but precise editing. It's actually easy to use (hello CensorgramV4!) and good.
Even in complex multi people scenes with multiple interactions, where Flux.2 Klein 4b and 9b and even dev may make already a mess of limbs (nevermind Ernie image...) , i've only see a messed up arm once or twice. This is ( in THAT aspect) possibly the best at that i've seen in several months (Flux1 was better with anatomy than2...) .
And you can just ... write some prompt and it works!
"Why not just use Z-Image Turbo or X for the quick image?": TL;DR Because Boogu is actually better (Boogu Fp8 base+lora >> boogu turbo model) . While also being quite fast. It is only NOT better in image quality (sharpness, texture, nitty gritty realism. .
So there still a case to use it (or seedvr) to improve boogu results visually. talking skin, fabric, materials texture and general image sharpness. That Z-grittyness™. But even the image quality is actually ok now. Even at 4mpx which they do not recommend.
While Z-image is quite ok with anatomy, even it messes things up more than Boogu. and it throws it's hands up when a scene gets too complicated. Also Z-Image of course has no editing function at all.
Not so convinced of the Boogu Turbo model. Maybe a settings thing but it lack in image quality. Since i can ran base+lora very fast, i do.
I'm often using the editing model, just with reference images for people and so on for completely newly prompted (complex) scenes but with the reference person/clothing or whatever involved. Same works of course For Flux2, QE and others). Using them just to edit an image is a criminal underuse.
Likeliness in Boogu Image Edit is not perfect but works well enough for that. And because it is so good at anatomy it is good at putting reference subjects in different situations.
So for that reason it's very similar to the non edit model. When using non edit, i use mostly base models+turbo lora. lora 1.0, 10to maybe 14 steps, pretty good image quality.
Since i have now q few loras i use the actual base model (int8_convrot+lora) more now.
The results are a lot better (i.e. closer to the prompt) without the speedup lora. But then it takes of course much longer (base fp8/int8 edit model). It's still fairly fats for a non distilled base model. But again, in challenging multi people interactions it (then) messes up anatomy less than Qwen (things like additionally hands placed somewhere nonsensical...) .
Generally: Hands even in fairly complex situations are mostly alright. And in simpler situations they are always alright. Arms and legs are basically always correct. peoples position and interactions make visual sense. Weird clothing glitches and alike are also rare. Even when using people from reference images. This is well beyond Flux Klein4b and even 9b and dev in Anatomy, (but still off them in image quality!).
In precise editing tasks, that change only what is wanted, flux2 (klein) or quen image edit remain the better choice..
Of all the recent models i know, Boogu feels the most underrated. It is good, AND it is easy to use. That has become rare!
- ideogram needs a fricking script as prompt. WAY too much hassle. and doesn't seem to come with much benefit. Except maybe for text heavy infographics and stuff.
- Ernie image is just ... shit. It couldn't make a correct person (2arms, 2 legs, 10 fingers...) just standing there. And it turns everybody chinese, no matter what you prompt. It also feels vastly less flexible and capapble than boogu in general.
- hidreamO1: looked interesting, but extremely low detail and blur in large ares (skin, clothing texture) , only useful with heavy postprocessing/upscaling. too much hassle while no advantages (ok lora trainign is FAST). .
- longcat image not really tried. Seems very fast but nothing special.
- there is a joyai one coming to comfy main (hopefully) that looks interesting because it is actually large, while everything else seems to go the XB turbo mode. Hoping for a new qwen image edit, but likely won't get it...
With Boogu being officially 0.1, i hope it gets better over time without messing up what they already have. this is a good base!
Training:
Sadly Boogu trains considerably slower than HidreamO1 (which is the fastest training (modern) model i know). Arguably Hidream images are so low detail in textures and stuff, that's probably why it learns so fast. But HidreamO1 is quite good for some things, like using people as reference images, and because of the fast training ( it/s AND iust 200-400 steps needed) ), for the quick person lora, that remains my new goto (to then be heavily post processed.
HidreamO1 it is not remotely as flexible/creative or ...good at creating new scenes as Boogu though, so it can only do (relatively) simple.
*Talking of kinkiness: unlike any model but Chroma1Hd, it knows what handcuffs look like :P