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 38,716
Outfit Packs Part03 - Honkai Impact 3rd (34 Outfits)
You can view previous Outfit Packs in the Collection tab. This is the 3rd Installment as I've decided to limit each LoRA Page to 7 Packs.
Still in Love - Umamusume Pretty Deby
这是一个《Umamusume Pretty Deby》 《闪耀 优俊少女 》 的爱如往昔角色LyCORIS。
Genshin Style pony and noob
以原神剧情pv为训练素材的一个风格lora,目前仅使用了蒙德出场的部分角色作为训练素材,本模型仅供娱乐,请勿用作任何商用与违法行为,后果自负。noob版本基于eps1.0所训练,出图预览为eps1.1
Pencil Sketch
Stop prompting from scratch, explore 10,000+ Prompts for free 👉 PromptDexter.com
Plant Milk 🌿 - Model Suite (Walnut)
recommended to try Euler and Euler a samplers first. (3-5 cfg, 28 steps)
Takamichi Style Alternative ANIMA
A LoRA inspired by the art style of illustrator Takamichi.
Alicia - [II’ll Become a Villainess Who Goes Down in History] - Illustrious / SDXL / Pony / SD15
Alicia - [II’ll Become a Villainess Who Goes Down in History]
WoW_(XL+PD+Flux).
The latest version has a bit less style, more realism. But with better anatomy.
Vector Icons - Game Assets LoRA
Resolution: Best at 512x512 (native training resolution). Also works on 768x768 for more details but may have some flaws.
[+]XL 池仓玛丽娜 / Ikekura Marina / 池倉マリナ | Blue Archive
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently...
Encode Chrombpnet DNASE ENCSR842KCP ENCSR293JHJ
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.
Framecore Polytope LoRA
Developed by: [More Information Needed] Funded by [optional]: [More Information Needed] Shared by [optional]: [More Information Needed] Model type: [More Information Needed] Language(s) (NLP): [More Information...
FLUX.1 Krea Dev DF11
🚀 Fully Lossless – 100% identical outputs to the original model 📦 32% smaller model size – lower VRAM requirement than float16 ⚡ Compatible with ComfyUI – drop-in support with custom nodes 🔧 GPU-accelerated...
NexusDream*INFINITY
✨Introducing NEXUSDREAM INFINITY , the best groundbreaking Stable Diffusion checkpoint engineered to be your ultimate all-in-one base model. Trained on a meticulously curated dataset, this model excels across a vast...
[SDXL] Artist Style: Kawakami Rokkaku/川上六角
SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.
[GTO] Uehara Anko 上原杏子 (Mange Style)
V2: Minor stability improvements. If you're happy with v1, feel free to stick with it.
ColourfulCartoon - LocOn
Trigger world - ColourfulCartoon every second immage is the model and the first immage is without
Who's That Girl? 오늘의 한요일은 여자다 - v1.2
Trained almost all "Who's That Girl?" Characters.
加護のあ Kago Noa(Pure Love Girl) Anima
KagoNoa, 1girl, solo, pink hair, blue eyes, short hair, hair ribbon,
Rio 3.5 Open 397B NVFP4
NVFP4-quantized build of prefeitura-rio/Rio-3.5-Open-397B — a 397B-parameter (17B active) Qwen3.5-MoE vision-language model (512 experts, hybrid softmax + linear/DeltaNet attention), itself a finetune of...
