Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Resource directory
Search Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
20 shown of 28,883
This repository contains the llm.pt checkpoint fine-tuned on the Singapore Mandarin subset, as presented in the paper Joycent: Diffusion-based Accent TTS without Accented Phone Prediction.
本 LoRA 为《王者荣耀》相关角色/皮肤的同人模型,仅供个人学习、研究、交流与非商业同人创作使用。相关角色与美术形象的版权归原版权方所有。本人不拥有相关版权,本 LoRA 亦非官方内容,未获得官方授权。禁止将本 LoRA 或使用本 LoRA 生成的内容用于任何商业用途 Krea2: 推荐 LoRA 强度:0.9 Recommended LoRA weight: 0.9 推荐步数:8-10
This is a MXFP4MOE quantization of the model UI-Venus-1.5-30B-A3B
weight 0.7 works well
This is a 16-bit version of Qwen/Qwen3-VL-2B-Instruct fine-tuned specifically for Persian text recognition (OCR) on individual text lines. The model has been trained exclusively on cropped single-line text images and...
Character from "Miraculous: Tales of Ladybug and Cat Noir"
There is a secret place in a hidden spot, where a man spent countless hours to train a custom checkpoint to make beauty from a fart in the text-box. In this poetry of a model, behind a thick veil of neurons there...
A self-contained, fixed-revision Core ML build of the Kokoro-82M 7-stage Apple-Neural-Engine pipeline packaged with all 54 standard Kokoro voices, so a sandboxed Swift / Core ML app can offer every voice on the ANE...
| Model | FLOPS | Params | F1 Score | Threshold | F1 Plot | Confusion | Labels | | censordetectv1.0n | 898 | 3.01M | 0.8 | 0.278 | plot | confusion | nipplef, penis, pussy | | censordetectv1.0s | 3.49k | 11.1M | 0.83...
A LoCon model for generating Thing from Wednesday/The Addams Family. It can be used like a normal LoRa, but might also influence the image composition. Some common gestures like "clenched hand", "index finger raised"...
Works best at 0.95 weight.
