ATTENTION: The LoRA version is NOT a checkpoint, but a LoRA for local gen.
UPDATE3: δ is the latest revision of this checkpoint. This time, I took back a step toward crazyness, especially since i was experimenting with LoRA merging with a similar technique to Ties:
def isolate(a: Tensor, d: Tensor, k: float):
sign_filter = (a.sign() + d.sign()).abs() / 2
filtered = d * sign_filter
k = max(int((1 - k) * filtered.numel()), 1)
k_value, _ = filtered.flatten().abs().float().kthvalue(k)
top_k_filter = (filtered.abs() >= k_value).float()
return filtered * top_k_filterNothing more to say, please enjoy! 💜 (PS: this time, i took the time to upload the BF16 version, INT8 is coming up. There is an EA price, but you can pay in blue buzz, it is more to block bots...)
UPDATE2: Not much change in γ, still working toward keeping the look i like but correcting small quirks.
UPDATE: β is a less "white sticky fluids glazed" version of α 😁

μKrea2 (mu - Krea2) is my own final Krea2 mix based on several trained LoRAs (including nKrea) and some extracted LoRAs made as an experiment of hacking sd_mecha and learning how to unquantize INT8-ConvRot checkpoints (because undoing stuff is the best way to learn of to make stuff).
And since both the following events happened:
I finally found out how to convert stuff to INT8-ConvRot (via convert-to-quant),
stable-diffusion.cpp is now compatible with INT8-ConvRot,
here it is for your enjoyment!
I am releasing it as Early Access at low Buzz price to avoid immediate scraping.
Since this is Krea2 checkpoint, nothing special on usage, here is just some info on how i use it (for the showcase pictures for example):
ER_SDE/Smoothstep (aka Beta)
CFG 1 - 8 Steps
VAE: HDR VAE by @Felldude (basically the best FP32 VAE for WAN2.1/ANIMA/Krea2/Qwen Image)
All pictures made using stable-diffusion.cpp version master-874-656a135-2-g2ea8aff, commit 2ea8aff, compiled from source on ubuntu 26.04 with CUDA 13.2 with an RTX 3060 - 12GB. Each 960x1440 px pictures generated in around 60s (including decode).
Command line used (to start server):
./sd-server -l 0.0.0.0 -p "" -n " " --sampling-method er_sde --scheduler smoothstep --steps 8 -W 960 -H 1440 -b 1 --cfg-scale 1 -s -1 --clip-skip -1 -t 0 --rng cuda --sampler-rng cuda --diffusion-model muKrea2-INT8-convrot.safetensors --vae finalcut_vae.safetensors --llm Qwen3VL-4B-Instruct-Q8_0.gguf --vae-tile-overlap 0.5 --vae-tile-size 32x32 --offload-to-cpu --vae-tiling --fa --eager-loadAll pictures batched using a small custom sd-client that talk to the server using the API endpoint (i'll release it if someone wants it).
./sd-client --help
Usage: sd-client [-s "832x1216"] -o output.png -p "A picture of a cat"Thanks for reading!
Special thanks (for the great pictures they make that helped me find a direction for this):
@llikswonskcalb
@ElectricDreams
@Chumple
@lonecatone23
@Sophorium
@daceheg192491
@Liant
Description
Posted on Civitai, upload found elsewhere are FORBIDDEN and done without the author permission.



















