Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
20 shown of 38,509
Anime Head Detection
| Model | Type | FLOPS | Params | F1 Score | Threshold | precision(B) | recall(B) | mAP50(B) | mAP50-95(B) | F1 Plot | Confusion | Labels | | headdetectv2.0xyv11 | yolo | 195G | 56.9M | 0.93 | 0.458 | 0.95942 |...
seedvr2_ema_7b_fp16.safetensors
Wan2.2 - T2V - Pillow Humping v3 - HIGH 14B.safetensors
Merger_raine_marsoa
Another merger and the final party to the marsoa trio.
Whisper Uzbek Medium Callcenter
A Whisper-medium model fine-tuned for Uzbek speech-to-text, with data augmentation aimed at telephone / call-center audio (narrowband, noise, reverb) and anti-hallucination training on non-speech segments.
checkpoint.pt
Bree_MXAI
Bree doesn't exist, but was trained on a variety of blonde women
Siglip2 So400m Patch16 Naflex
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved semantic understanding, localization, and dense features.
instruct_only_mllm_encoder_bf16.safetensors
Sft Chatbot Arena Qwen3.5 4b As Gpt Oss 20b Seed42
Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 42.
model.safetensors
领航员 22娘 BML PLAY!2026 22niang Navigator.safetensors
iGoon_Blink_Missionary_Choking_HIGH.safetensors
Quelmdn Style
Works best at 0.75 weight.
天野和美 Amano Kazumi トップをねらえ!.safetensors
Misaki Style
Works best at 0.75 weight.
model.safetensors
Minicpm5 1b Math LoRA
This repository contains a math-focused PEFT LoRA adapter based on [openbmb/MiniCPM5-1B]( openbmb/MiniCPM5-1B).
