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 27,462
If the original artist requests a takedown, I will immediately remove this model off of CivitAI. Thank you. Please support their work here. Meanwhile, please do not monetize your generations.
So I wanted to do something different and take all these different images I’ve collected in different trainings and create something. This became the Mix person series.
LoRA of the mutant Slithe from the 1985 Thundercats cartoon series. Trained with Illustrious XL and Anima base model.
Everything here is free and stays free — the format spec, the nodes, the workflows, the cartridges, the LoRAs. If it saved you a night of debugging (it contains several hundred of mine), tips keep the 5090 warm:
The Spanish mix is an embeding trained on 98 images of Spanish models, one image for each, so it looks like none of them but captures their commonalities.
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...
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...
LoHA model for TRS sister. It is seems like the background is overbaked so you may add more prompt to background, idk.
This is another LoRa I had in the backburner for quite a while. I wanted to wait until my technical problems were resolved but that hasn't happened so I'm gonna have to release it as is. I'll post a Tensor link where...
Gilded detail, candlelit stone, and skin that reads like skin - without giving up anime structure or prompt adherence.
Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord
Trained on AOM3. This is a LoCON/LyCORIS, so please install the appropriate extension to be able to use it.
A textual inversion that draws on the Desi Coffee dataset to produce women with Indian features and medium skin tones.
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 !
Train based on AnyLora model. Training materials are basically official arts and pixiv artworks of 萩オスさん .
Trigger word: rodion Optional words: blue eyes, brown hair, long hair, white shirt, collared shirt,black jacket
Originally posted to HuggingFace by sd-concepts-library REPEAT on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable Conceptualizer...
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...
While there are already some Hanfu models on civitai, no one has ventured into the realm of the guzheng instrument. Therefore, I selected 40 images of Hanfu and 20 images of guzheng to train the Loha model, creating...
Behold Enhanced. I don't wish to spoil the fun, and mystery, so I will let you experience it for all of its glory yourself. Tweak the weight as needed, and use the trigger word in various spots. Most of all, have fun.
