Find what you need for your workflow.

466103

Exact lora artifact distributed with Miyao Miya 宮尾 美也 / THE IDOLM@STER MILLION LIVE! アイドルマスター ミリオンライブ! (v1.0 (Pony)).

27819

Exact lora artifact distributed with djx Super Rangers [ LYCORIS ] (v21).

Wan2.1_14B_VACE-Q8_0.gguf

Pov Shadow / 主観の影

This LoRA helps generate shadows from a first-person perspective.

steps_150000_pytorch_model.pt

Lucky☆Star らき☆すた 幸运☆星 主角团4位 --animagineXL

This LoRA can render four characters.Use Romanized words as Trigger Words.

ho'olheyak arknights 霍尔海雅 明日方舟

The current version is not perfect and there are still parts that cannot be completed. A better version may be released soon

SNOFS (Sex, Nudes, Other Fun Stuff) (Qwen v1.3)

Further training

Ll v4 5 16 Surface Naturalness Repair 20260625 Model

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct. It has been trained using TRL.

[+] XL Ajitani Hifumi/ 日富美 / ヒフミ blue archive

The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently...

Wan2.1_FusionX -The LoRa (Text2Video_FusionX_LoRa)

Fnaf Characters Ilustrious Edition - IL-Lolbit

Want to support me without Tipping? Here's how:

GR00T N1.5 3B LeRobot

This repository contains a LeRobot GrootPolicy checkpoint initialized from the original nvidia/GR00T-N1.5-3B parameters. It is intended to make the base GR00T-N1.5-3B model loadable through LeRobot's...

Princess Latifah Fleuranza - [Amagi Brilliant Park]

Princess Latifah Fleuranza - [Amagi Brilliant Park]

Gemma 4 26B A4B It Qat Q4 0 Unquantized I1 GGUF

For a convenient overview and download list, visit our model page for this model.

anima qingwei style

更新:这次是从base开了一个新分支,使用的是懂得都懂的训练集和懂得都懂的美学集,反正能画懂的都懂的东西,特长和v1.0不一样,应该是封面图那种和可以联想到的那种,但是我自己不喜欢和civitai审核斗智斗勇所以发的都清水图,你们自己开发吧。 更新:前面一个版本的结果使我能够确信我实验的方法论有一个好的结果 所以在这个正式版本,我认为我可以使用我那个2.5w的图数量的正式训练集达到一个不错画风微调 这个版本使用2.5w的非生成数据训练,并且依旧沿用上个模型的1200图的美学参与 比较anima base我觉得拥有一些我训练后的更偏向我喜好的画风质感,并且手指和脚趾比原版好稍微那么一丢丢,至少我通过xy图表看是这么一个效果,而且其实我自己测试下来,并没有失去对base model的Lora的兼容,至少我训练的Lora通常rank比较低,依然是有效的,而且画出来还行 旧版本:微微调的anima base,改善了一些美学,使用了ai生成数据,我人工筛选了所有的图片以确保训练集的质量,都是我生成造出来的图片 并且,我把自己的画风,训练过一个tag了,可以使用@qingwei画师串 仅训练dit的方法下训练的,冻结一些模块,不会出现如同融模一样的anima本体的知识被损失的问题,仅仅是如我说的那样微微调了美学

My Wnut Model

This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.2778 Precision: 0.5603 Recall: 0.3142 F1: 0.4026...

196689

Exact lora artifact distributed with Rina Tennoji (Love Live) LOCON (v1.0).

Qwen3 5 9b Full Sft Prm R2egym Swebench Instructions K5 Cwm Plus Qwen

This model is a fine-tuned version of Qwen/Qwen3.5-9B on the prmsfttrain dataset.

Detr Resnet 101

> Carion et al., 2020 — End-to-End Object Detection with Transformers (arXiv:2005.12872)