Find what you need for your workflow.

Boltzgen Adherence

OFoldX pipeline artifact for biomolecular design generation, using the boltzgen-adherence architecture.

Dengeki Bunko Sprite Style [Illustrious]

Dengeki Bunko Sprite Style. Trained on Illustrious-XL.

Still in Love - Umamusume Pretty Deby

这是一个《Umamusume Pretty Deby》 《闪耀 优俊少女 》 的爱如往昔角色LyCORIS。

Haruka - [Enokido] Seiyoku Tsuyo Tsuyo ([エノキドォ] 性欲つよつよ)

gyaru haruka, long hair, bangs, blonde hair, (yellow hair:1.5), (pink eyes:1.5), earrings, mole, mole under mouth,

Skin Tone Slider - (Krea2 + ZIT)

V1 was a little unstable at high values regarding ethnicity. That problem is fixed on V2 .

Alejandra "Patches" Coldthorn (Chalo | Las Lindas) | LoCon

I have opened up a request form

Qwen-Image-Distill-Q3_K_S.gguf

Cute comic style (Jojo)

Original art is from the franco-belgian comic Jojo by André Geerts

wan_alpha_2.1_rgba_lora.safetensors

Hakam 0.8b Sportsqa Distill LoRA

We trained a 0.8B model to match a 27B model on sports video question answering. Same test accuracy, 30× smaller. It runs on a normal gaming GPU. That's what knowledge distillation buys you: the big model's skill at...

egirlcore style Aesthetic

(Please forgive the mess, using Civitai to host these LoRAs with different training settings to compare.)

Tiefling Concept LyCO

Trigger word: Tiefling This is my first Lycoris! I created three versions that resulted from different training settings of the same dataset. A soft, mixed and harder version of the concept. Please share and enjoy

Adepta Sororitas (Sisters of Battle) Warhammer 40K | Flux + Anima + Krea2

This LoRA is for Krea2, FLUX.1 [dev], and Anima, it's made to give your character the Sisters of Battle power armor from the world of Warhammer 40K.

ThinkingCap-Qwen3.6-27B-heretic-Q5_K_M.gguf

DonutsDeliveryMix V4 - NSFW Photorealism

Also try my new checkpoint:

ace_step_1.5_turbo_aio.safetensors

25150

Exact lora artifact distributed with [LoCon/LoHa] nslacka Style (LoCon v1.0).

Clip 336 LLama 3B Llava v3

This model is a fine-tuned version of []( on an unknown dataset.

Gin_moku Style

Weight looks good around 0.6-0.8, perfect value i find for myself is 0.7, try starting from here. ADetailer strongly recommended. You might want(not necessary) to use flat 2d models such as Sudachi or use suitable...

Kemono Fursuit LoRA | Furry style realism

I'd love to see what amazing creations you make using this LoRA!