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 29,828
This model is released under Fair-AI-Public-License-1.0-SD Plz check this website for more information: Freedom of Development ( freedevproject.org )
I present to you Naruko Uzumaki or the rule 63 of Uzumaki Naruto, This is the LOCON version of my Naruko LORA . Along the years I have heard a lot of people comment that had Naruto been a girl(or gay i guess) a lot...
This repository contains the Qwen3-TTS-Tokenizer-12Hz, as presented in the paper Qwen3-TTS Technical Report.
This is the SDXL version model for Skuld from Ah/Oh My Goddess. Since it's based on SDXL, it only works correctly with compatible models.
您应该将下载到的负面文本嵌入文件置入您 stable diffusion 目录下的 embeddings 文件夹内。之后,您只需要在填写负面提示词处输入 badv4 即可。
Style based on artist Azazel1944's works, specifically on the 79 earlier warcraft-era works, though every other image up to the present day ( 111 in total) has also been tagged and is included separately in the...
Trained on 29 plein air paintings by the British artist Dorothea Sharp ROI RBA (10 January 1873 – 17 December 1955) [1] . She was a British artist best known for her landscapes and naturalistic studies of children at...
Marlena is the latest of my models trained entirely on prompted images, no humans involved. Trained on 76 prompted images, 15 vectors, learning rate 0.004, 15 steps pr image/embedding and 1650 steps in total....
Does the style of Lupin the Third: The Woman Called Fujiko Mine. Fantastic colors, eyes and hatching textures. Combines 1970's retro look with modern style.
A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone
neutral colored animevae. only animevae(100%) on feat new technology, half size pruned to only statedict(rest keep losslogver).
This is a Textual Inversion i've made for fast photo-realism.
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.
Trigger words are: VanguardCEmblem Additional words that may help: simple white background, A description of what you want Recommended Strength: 1.0
Train based on AnyLora model. Training resources include official arts , leader's spine animations and some fanarts from Shadowverse.
If the original artist requests a takedown, I will immediately remove this model off of CivitAI. Thank you. Please support their work here. Meanwhile, do not monetize your generations.
They say that blondes have more fun. It's up to you, dear prompters, to decide whether this is true or not, at least in regards to this mix.
This finetune should improve coherency when generating humans
I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated:
This model was created as an experiment by simply aggregating the learned content of various models (this test using "Anima" models, chosen for their lightweight nature). The process involves iteratively combining...
