Find what you need for your workflow.

XL Miura Azusa/三浦梓/三浦あずさ Idolmaster/偶像大师

Base Model: Animagine XL V3.1

Diathorn style, LoRA, Anima

A drawing style Lora of Diathorn

GTA Art Style

The model has two different subsets.

Tower13 Girls - Imani

TOWER 13 GIRLS (PART 038)

Abawuwao

Saw a request for this in a discussion, direct GGUF conversion of base model which is a finetune of Wan 5B.

Artist Style: torino

The training set comes from torino.

Tower13 Girls - Polonia

TOWER 13 GIRLS (PART 063)

Whisper Tiny Khmer

This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set: Loss: 0.0702 Cer: 21.3240

Oboro Tsukimigusa | Shimoneta

Works best at 0.6-0.65 weight

Cocoballking Style (Anima & Illustrious)

Works best at 0.75 weight.

Qwen2 VL 2B Instruct Abliterated 4bit Mlx

This model was converted to MLX format from huihui-ai/Qwen2-VL-2B-Instruct-abliterated using mlx-vlm version 0.6.5. Refer to the original model card for more details on the model.

Stt Hy Fastconformer Hybrid Ctc Large GGUF

GGUF conversions of the CTC branch of nvidia/stthyfastconformerhybridlargepc for CrispASR. The upstream model is a hybrid transducer+CTC Armenian ASR release; the shared FastConformer encoder plus the auxiliary CTC...

[PonyXL] Nui Sociere/ニュイ・ソシエール/纽伊·索西艾瑞-彩虹社/Nijisanji/にじさんじ Vtuber

High frequency word: nui sociere:1.00

ttosom Style

OC-a31-xingqiu-girl

只使用一张图在animagineXL3.1训练的娘化行秋,推荐使用a3.1作为底模,lora强度为0.8,具体prompt见示例图。单图训练属于极端情况的实验产品,可能会存在许多问题。

lamia

Lora to print a simple lamia

Ruoganzhao Style (Anima & Illustrious)

Works best at 0.75 weight.

Fridge Tank (KV-2) LoCon

I have opened up a request form

Mora Linda (Chalo | Las Lindas) | LoCon

I have opened up a request form

Rishe Weitzner - 7th Time Loop

Rishe Weitzner - 7th Time Loop