Find what you need for your workflow.

qwen_image_fp8_hq.safetensors

Pittman/彼亚塔曼/ピアタマン---Alchemy Stars/白夜極光

北沢留美&北沢智子 Kitazawa Rumi&Kitazawa Tomoko (Ai Simai Futari no kajitsu) Anima

KitazawaRumi, 1girl, blue long hair, blue eyes, medium breasts,

xl_kono dio da (meme)

kohakudelta使用 Kohaku-XL Delta - rev1 |稳定扩散检查点 |奇维泰

481776

Exact lora artifact distributed with ReiSaiga (shangri-la frontier) (illustrious).

Ichihara Nina/市原仁奈(for ponyXL)

brown hair,long hair,blunt bangs,brown eyes,flat chest

PaddleOCR OpenVINO

将 PaddleOCR PP-OCRv4/v5 模型转换为 OpenVINO IR 格式(.xml + .bin)。 支持通过 PaddleOCR-OpenVINO C++ 运行时 在 Intel NPU / CPU / GPU 上进行本地推理,无需联网。

Smollm2 135m SAE

license: mit language: en basemodel: HuggingFaceTB/SmolLM2-135M tags: sae mechanistic-interpretability sparse-autoencoders monosemanticity feature-extraction smollm2 interpretability atlas pipelinetag: feature-extraction

Cerise Bianca, Ladybug, Miraculous. Different models and attires.

🟣 Hi everyone, I wanted to take a moment to talk about the future of my work and this channel. Dedicating so many hours to creating and refining LoRas is becoming increasingly difficult to sustain every single day....

Twinkle VAE

best of best than past all-things(vae, except for apricots series)

GREED (Greed Bf16)

17336

Exact lora artifact distributed with Roukin8-character-LoHa/LoCon/FullCkpt ろうきん8 (LoHa).

mova_360p_low_noise.safetensors

witch lady ウィッチレディ (DQ8)

This is a Loha file for the Dragon Quest 8 character, Witch Lady.

Fantasy Action

This lora aims to create images within the fantasy world. The idea was to create something which has some action or at least an action stance. Also, it should be able to do solo focused pics as well as big crowds or...

Qwen-Image-Q4_K_S.gguf

Wan2.2-Fun-Camera-LowNoise-14B-Q3_K_S.gguf

Visualrl LoRA M2 Only

152892

Exact lora artifact distributed with Rozen Maiden 翠星石 suiseiseki - LoCon LORA (v2.0).

Llama 3.2 Mavrick.Spark 1B

A fast, edge-friendly 1.23B parameter model that distills the Spark-style persona (concise, helpful, agentic vibes) and Maverick long-form reasoning traces into Meta's Llama 3.2 1B Instruct base.