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 27,020
Discover the magic of Babes V5 by Stable Yogi ❤ , a part of our Instagram Influencer series by StableYogi. This tool is designed to bring your digital creations to life with stunning clarity and artistic flair.
rhea fighter, (green eyes:1.5), hair ribbon, ponytail, red hair, pointy ears, elf, white bow, white ribbon, ribbon,
pokemonsonia, aqua eyes, heart, heart hair ornament, long hair, long sleeves, orange hair, side ponytail, swept bangs,
I'm glad to share with you my latest experiment, a basic camera motion LoRA trained with 32-frames on an Animatediff v2 model. The training process utilized Kijai's AnimateDiff Motion Director ComfyUI nodes . This...
v2 Preview: 更新了训练集内容,将大量带有审查的图片替换为无审查图片,优化了在微调模型上生成图片的效果,但是因为原素材集有大量湿润皮肤与汗液,在这个新的模型上也会容易生成这方面内容。 我还在想办法解决这方面内容。 推荐nsfw生成使用 Muse By Stable Yogi Krea2 模型,我测试过在这个模型上生成的图片不会偏向真实质感,其余模型自行测试。
Train based on AnyLora model. Training materials are basically official arts,fanarts and game resources from Cygames products.
Style of 2004 GITS movie. Focus on gynoids, androids and mechanical parts. (anime screenshot) for maximum effect. Also does Batous basset hound really well.
This is a textual inversion I trained to try to better emulate the style of Edward Hopper. It includes paintings and sketches and one or two portrait done in the style but not by the artist.
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.
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.
Ava. I won't engage is some fantastical fictional account about who this character is. I'll let you fill in the details. I made her because... well because who doesn't like blondes?
Oh no is your character being to bitchy and mean? I think it needs a little bit of softening up. Let's put it into the taffy-pulling machine. The lora works with different characters!
Latest page update: Updated recommended workflow again to a version 2, which is slightly even better.
“Hekoheko” (ヘコヘコ) is a sound effect used when a character is unable to control the movement of their hips due to excitement or other reasons.
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...
Why create an embedding about my succesful model? Because is funny xD. It returns images with a 2010s horror and fantasy style illustration.
The first Lycoris Model is an experiment for use comparing Captioned/non-Captioned dataset vs the LORA counterpart version (DB2 LORA's are not captioned either)
Utagawa Hiroshige (1797-1858) was a Japanese artist in the ukiyo-e tradition, considered the last great master of the form (which translates roughly as "pictures of the floating world"). His most famous works are The...
Honey Glaze is an Illustrious model with high-clarity anime–model that pours a warm, glossy sheen over every character it touches. This checkpoint leans into polished skin textures, soft cinematic lighting, sharp...
A LyCORIS model trained on images of Iwakura Lain from Serial Experiments Lain, for AnimagineXL 3.1.
