Find what you need for your workflow.

Nice Nature (umamusume)

Aesthetic Amateur Photo

Nova Anime XL (IL v19.0)

model.safetensors

Webssl Dino3b Heavy2b 224

A 3 billion parameter Vision Transformer (ViT) trained with DINOv2 self-supervised learning on heavily filtered web-scale image data without language supervision. Introduced in "Scaling Language-Free Visual...

Llama 3.2 11B Vision PokemonCard OCR LoRA

This is a Vision-Language Model (VLM) fine-tuned from Llama-3.2-11B-Vision-Instruct to perform Optical Character Recognition (OCR) on Pokémon trading cards. The model is trained to extract card names and card numbers...

model.safetensors

Pall Wash - A Versatile Dark Fantasy Anime Style [ILL/ANIMA/KREA 2] (Illlustrious)

kodoranimem_v26.safetensors

hard_cut_2_100_wan_i2v_high.safetensors

Maegami Chan (Tawawa On Monday)

Maegami Chan, Tawawa On Monday

sexy-massage-wan22-LN-e33-az420.safetensors

神椿市建設中 harusaruhi.safetensors

model.safetensors

Qwen3 Asr 1.7b Onnx FP16

An fp16 ONNX export of Qwen/Qwen3-ASR-1.7B, packaged for sherpa-onnx (OfflineRecognizer.fromqwen3asr). Intended for GPU inference (CUDA execution provider): 4.5 GB on disk / 4–5 GB VRAM, roughly half the fp32 export,...

ltxv_0.9.5_vae_fp16.safetensors

Finetune Donut Cord v3

This model is a fine-tuned version of naver-clova-ix/donut-base on the CORD v2 (Consolidated Receipt Dataset) for OCR-free receipt understanding and structured information extraction.

Photo Regenerator

Incrementally adds noise over a series of steps via a noise scheduler, and feeds images through a CNN to learn features/patterns to then "regenerate" the image.

model.safetensors

V67 Natural color palette

V67 Natural color palette – 🎨🌾 – LoRA for Z Image Turbo and Krea 2.