Nothing interesting going on here, move along.

Just a small finetune of Anima, 4 epochs with 12k images. Nothing interesting was done. Is more 2.5d, will lead towards more abstract, that's about it.

Issues

Can have strong bokeh in some cases.

Some wide shots are transforming into less common compositions for which there is barely any data and denoise fails hard on them.

Positives

Tends to add more details.

Elements in the scene usually interact more (i.e. abstract features affecting more concepts)

Some complex compositions become better defined.

Booba is bigger on average. (But i will not benchmark that(for now))

Less common concepts with abstract meaning may perform better (like horror)

Other Features

On average, less overwhelming contrast, dimmer.

Can use higher cfg without blowing out colors (i use 5-6, vs 3.5 on base), but not required.

Params i use

dpm++ sde, 16-24 steps, cfg 3.5-7, shift 4

How was it trained

Lr: variable LR per block group, from 3e-6 to 5e-6, from early to late.
Adapter: frozen.
Loss: L2, with some modifications for rare aspect ratio buckets and depth.
Schedule: Logit-Normal -0.2 1.5(or was it 1.5 -0.2...)(Bluvoll's schedule) with shift 4 and normal tail sampling modification. (Tldr, all that fixes lack of front in default logit normal and normalizes amount of sampling at the very late timesteps, without making them overbearing at high shift.)

Captions: tags only. (you won't make me suffer through captioning 12k images with gemma 4 31b or qwen 3.6 27b locally for NL counterpart)

Examples

Anima base 1.0 on left, this fintune on right.

Samples are using same parameters, except cfg in some cases, as i was discovering what cfg works better for this finetune. It did not affect composition in a significant way though, so it's whatever.