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
19 shown of 26,845
ryou yamada, blue hair, eyes visible through hair, mole, mole under eye, short hair, (yellow eyes:1.5), hairclips,
For characters with many hair accessories or diverse hair colors, the color of the hair wrapped in rollers may appear strange. While this can usually be corrected by editing with the detailer, inpainting may be...
If you'd like to support me and do more: commissions open! If you're looking for a >>LoRA Making Tutorial
Have been wanting to make a robot concept for a while so I made one. The name is a reference to gunpla ratings as this creates a moderate amount of details as expected of Real Grade gunpla. Actually had this finished...
This new technique will surely come in handy to many people, the images in the dataset are all solid red .PNG images.
Who is Hiroshi? Do you recognise him? You don't. He's a creation of Stable Diffusion and is here for your use in your prompts.
When I train a model I strive for a flexible model that allows for a lot of creativity with minimal "pain". Trained on NAI for anime model compatibility. For most purposes a weight between 1.0 and 0.9 will work well....
momo hinamori, black hair, hair bun, single hair bun, bun cover, short hair, (black eyes:1.5), (swept bangs:1.5),
This style adds glitchy artifacts to images. The images have a black and white with red accents color palette. Along with the trigger (n0vuschr0ma style), you can try adding phrases like "digital artifacts", "glitch...
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.
This is a Stable Diffusion textual inversion with vintage anime illustrations as a style. If you wanna test it, you can put this word on the prompt: oTZk.
This model is based primarily on an artistic style. The style is combined with different artistic trends, such as: black ink flow, an airbrush painting, beautiful fantasy art, calligraphy, acrylic, watercolor art,...
单一的触发角色标签不一定能起到良好的作用!训练时我没有移除任何的特征标签,也就意味着您需要使用比较详细的标签来进行还原。 常见的触发方法(以睡衣优香为例子) 1girl, solo, yuuka (blue archive), (yuuka (pajamas) (blue archive):1.3), blue archive, + 角色特征
I'm TonightXiaoJinXiao. My previous account got banned, so I had to start fresh. If there was a particular model you really liked before that's gone now, just let me know.
Version 2.0: Updated the dataset to my Anima Base outputs from the old Anima Preview dataset ⚠This version of the lora seems to have more issues with forgetting and I have been unable to identify the root of the...
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
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...
SDXL LoRA/LyCORIS works best on its original training model . You may need to reduce weight when using it with other models or additional LoRAs . LyCORIS Combination Recommendation: Try using four of my LyCORIS...
This is an embedding of a woman that I've generated consistent faces of thru SD and decided to make into an embedding for easier access in the future. It uses a mere 5 tokens.
