Find what you need for your workflow.

Whisper Small SIT 16 07 26 0300

This model is a fine-tuned version of Pengwin30/whisper-small-fine-tuned on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.0097 Wer: 0.3976

Genndy Tartakovsky Style Series for Pony

(scroll down for other versions)

118672

Exact lora artifact distributed with Lulu Suzuhara - Nijisanji - COMMISSION (v1.0).

Yangyang: Xuanling (Wuthering Waves)

V1-Limited images. Clothes quality is very poor. recommend to lower weight.

Nokoko / Koopa Gal (Minus8) - [Anima/IL/Pony]

UPDATE 07/28/26: Anima model version now available!

Llama 3.2 3b Instruct Ultrachat Sft LoRA Merged

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

LTX-2-19B-Dev-Q4_K_S.gguf

[PonyXL] Serial Designation V (Murder Drones)

I like my robot girls how I like my coffee, very capable of killing me

Goofballs

This LoRA was trained on still images of bizarrely distorted faces. I t responds to the word caricature and descriptions of exaggerated facial characteristics.

Wabori_tattoo

I created a Japanese-style tattoo in Lycoris. It is available for use with anime-style realistic models. However, the learning on the back might have been too strong, so please adjust it with negative prompts.

artist:murakami suigun

更新 一口气更新两个版本,一个是之前说的老画风,一个是新老画风在同一个lora里可以分开调用的多画风,老画风的启动词是@murakami suigun \(2000s\),而新版本是@murakami suigun。 另,我觉得双画风在一个Lora里会很炫酷,你们不觉得很炫酷吗。 以防你们不信以及不会翻到我证明一个丹两个画风,我把对比图放这 anima版本更新 其实anima会这个画师串,但是因为这个画师的画作时间跨度太长,所以取了比较新的时间的训练,这个Lora可以很好稳定在比较近期的风格,比画师串观感好的多,未来我会再炼一个怀旧画风的分支 V3更新 更好的还原度,更好的肢体,更好的兼容性,甚至更好的训练集 权重1.0 又新又好,啊不行我不能嘴角上翘。 V2更新 没什么好说的,全面的比1.0要好,建议直接换成V2.0。画风更像的同时还没有了以前老画风的污染情况,也不用将画师tag调成0.6-0.8了,并且兼容的模型我测下来更多了。 murakami suigun 的画师风格lora 权重建议0.6-0.8,注意,你的murakami suigun这个TAG也要0.6-0.8.原因是noob本身有这个画师TAG,但是学的不像又过拟合,这个lora主要解决tag不像的问题。 不使用启动词时是另一种风格

JiRack 10b

cms-manhattan-jirack-v1.4

Minori after SPPL art style (中二社SPPL后画风) | NoobAI

Please do not use any positive quality tags when using my LoRA. The essence of quality tags is art style. This is why your results are so different from mine, especially on illu base model !

Artist Style: Honnryou Hanaru(Anima.ver)

The weight can be used from 0.1 to 1

Wan2.2-Fun-Camera-HighNoise-14B-Q6_K.gguf

Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-IQ4_NL.gguf

Japanese Art Styles

Base model: Illustrious Trained words: F2n5ia

ニーソックス/thighhighs

ニーソックス とりあえず作ったものなので、安定しないです。 トリガーワードとして「striped,polka dot,star pirnt,heart print,print」を「thighhighs」と合わせて入れてください。 柄が服にも影響することがあります。

qwen_image_distill_full_fp8_e4m3fn.safetensors

[MB] Vol. 1 Custom Styles for Pony

See new CartoonPink Style Lora