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 26,956
Look : d0m1n4 , 1female, short hair, bob cut, black hair, yellow streak hair, asymmetrical hair, sharp eyebrows, winged eyeliner, eyeshadow, brown eyes, makeup, dark-skinned female, triangular crystal earrings,...
TanakaMisa, 1girl, solo, brown long hair, high ponytail, hair red ribbon, medium breasts, brown eyes,
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.
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...
Originally posted to HuggingFace by sd-concepts-library Jang-Sung-Rak-Style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable...
This is a DoRA , not your typically made LoRA . A1111 v1.9.0 and up is required to use this. Forge users must download two files, which can be found here . Go to stable-diffusion-webui\ldmpatched\modules and replace...
AUNTY VICIOUS Aunty Vicious is the aunt of of the Vicious family girls. Due to all the ruckus the girls causes she wanted to to show everyone what she got to offer at her age :-D. The Vicious family are nice people...
TemporalNet for SDXL is a specialized ControlNet model designed for use with AnimateDiff in vid2vid workflows. It ensures consistency between frames in animated sequences, maintaining coherence in motion and detail...
画风和脸部加入了我自己的喜好,使用起来很简单,即便什么画风tag也不加,直接出图的效果也很好,然后 它可以支持多画师串的输入 ,很多anima模型只能输入一个画师串,放多了图片会崩坏,这个模型没这问题,也就是说 你可以像以前使用Illustrious模型那样去进行多风格融合 ,这点我很喜欢。
Experimental textual inversion embeddings in a similar vein to the Boring Embeddings . Intended for use with Fluffyrock Unbound. They're intended to improve quality while not drastically altering image content. They...
At weight 1 to 1.1, you'll get tall, pretty buildings with tall windows (including some very distinctive looking buildings that could be streets along the water in Amsterdam). At 0.8, it'll lose the distinctive look...
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...
Please do not use any positive quality tags when using my LoRA. The essence of quality tags is art style. This is why your results are so different from mine, especially on illu base model !
Hey guys! Hope you love using this new LoRA as much as I loved making it. Just a quick word of advice: try not to go overboard stacking a ton of LoRAs together, or they will just fight each other and ruin the whole...
This LoRA is designed to recreate the unmistakable charm of vintage Fleischer-inspired animation , bringing the lively energy of 1930s theatrical cartoons into your generations.
SULEIKA VICIOUS Suleika is from the Russia. More than anything she is a True Vicious.... They are nice people and gave birth to a lot of pretty daughters, the best about them is... they are entirely fictional. WORKS...
So I have another merger from my TI's but as I have been using reactor and i2i to build these I thought about doing 2 from separate reactor models. so I have 2 version, mostly to see the visual difference this made...
raphtalia, animal ears, brown hair, long hair, raccoon ears, raccoon girl, raccoon tail, (red eyes:1.5), tail,
This model is trained on 12 images. Please leave feedback as I am still exploring in low-rank loras.
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...
