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 27,277
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.
Stupid Maximilian! Waifus are for lewding not for exploding! This is the LOCON version of my V2 Selvaria Bles LORA . Remember to curse Maximilian for being a fucking useless and retarded waste of space.
For image generation, I used the standard basic workflow without any additional custom nodes, except for a simple upscaler (feel free to use any upscaler you prefer).I went with the sampler combination ersde/simple....
USE ANY SD1.5 CHECKPOINT. WORKS BEST WITH THE TRUALITY ENGINE PRO I’m Stephanie, 21, half English, half Irish, and 100% fueled by the need for speed – preferably on four tiny wheels. When I’m not catching air at the...
Trained on 142 images (lower repeat on 3d/realistic images cause style was being affected). The dataset was oriented so the right side is jagged/designed and the left is straight.
Gabi is coming from east europe, long hair, big eyes, large eyebrow. Use better a full and descriptive prompt with this TI, even it's a light one. Note there are three versions with different training steps (100, 200...
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...
Who is Marcia? Do you recognise her? You don't . She's a creation of Stable Diffusion and is here for your use in your prompts.
Eutrope " Wicked Thunder " the final boss of Arcadion M4 from the MMO " Final Fantasy 14: Dawntrail ". Works best on 1.0 weight . Training done on Pony Diffusion V6 XL . Request form
Simple LoRA for greater sharpness, more texture, higher contrast, better skin tones, and a bit more detail.
The title with the "+" sign means that the data source has reached its limit within the capabilities of the me.
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...
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...
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:
Alina Clover - [I May Be a Guild Receptionist, But I’ll Solo Any Boss to Clock Out on Time]- Illustrious
Member of house Burion Secelia Dote from the anime " Mobile Suit Gundam the Witch from Mercury ". Works best around 0.8-1.0 weight . Training done on Pony Diffusion V6 XL . Request form
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 !
Another one of the sailor senshi in this particular case Minako Aino or Sailor Venus. This is the LOCON version of my Minako LORA . As most of my sailor moon stuff this is trained with mostly glamourworks, Kuroinujuu...