Find what you need for your workflow.

Recluse (Elden Ring Nightreign) - Illustrious

V4 Edit : I know I said V3 would be the last until the game releases, but I wanted to try local training. One other thing to note is that it's trained on Illustrious2.0-stable, rather than 0.1.

Liones Yelistratova / リオネス・エリストラートヴァ (ひなろじ ~from Luck & Logic~)

ひなろじ from Luck & Logicの他のキャラクターはこちら( ニーナ・アレクサンドロヴナ )。

Mangled Merge VAE

This VAE file can be used in conjunction with the Mangled Merge LyCo to bring out more color and make the image slightly darker and more contrasted. I haven't tried it on other models but feel free to give it a shot.

Kimi K2.7 Code DFlash

DFlash speculative-decoding draft model for moonshotai/Kimi-K2.7-Code, trained with SpecForge (PR #593) on NVIDIA Nemotron-Post-Training-Dataset-v2 (stem+chat+math+code).

FLUX Adapter FLUX.1 Redux dev (v1.0)

Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-Q4_K_M.gguf

Wan2.2-Fun-Camera-HighNoise-14B-Q8_0.gguf

clip_l_hidream.safetensors

flux1-canny-dev-fp8.safetensors

ACE (fp16)

DQ3 Priestess 女僧侶 | DRAGON QUEST III ドラゴンクエスト3

女僧侶「ドラゴンクエスト3」

ratatatat74 (ANIMA) | Artist styles | Mexes (Anima v0.1)

Parakeet Realtime Eou 120m Coreml

nvidia-open-model-license

Encode Chrombpnet DNASE ENCSR984SQJ ENCSR158MHO

As part of the ENCODE 4 Project, we trained ChromBPNet models on 1,512 ENCODE DNAse-seq and ATAC-seq across 408 biosamples. Here, we provide all models for open-source use.

PatBO - SS 2026 - Tulle Plunge Back Maxi Dress (anima)

紅葉

The strength of Lora is recommended to be around 0.8

Llama 3.2 1b LoRA Qlora Dart Llm

This model is a QLoRA fine-tuned version of meta-llama/Llama-3.2-1B specialized for robot task planning in construction environments.

Bert Finetuned Ner

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set: Loss: 0.2481 Model Preparation Time: 0.0021

steps_150000_pytorch_model.pt