Skip to content

Resource directory

Find what you need for your workflow.

Guides: techniques, setup, and troubleshooting

Search Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.

Start with a workflow instead ↗

Search results

All resources

20 shown of 38,761

ModelCivitai

Change-A-Character: Naughty Maid, Your Waifu Just Looooves Cleaning... Everything!

Note #1: I have been unable to post my Chikan, Train Groping, Locon here on CivitAI. Check out example images of it on twitter ( ) and download it there as well. May add some more Locon's that CivitAI doesn't allow...

loraStable Diffusion 1.5
Status
ListedD
ModelCivitai

Yufine (Epic Seven)

Yufine from Epic Seven.

loraAnima
Status
ListedD
ModelCivitai

Rolua - Artist Style

High-contrast painterly style with sharp sketch lines, glossy highlights, muted cool palettes.

loraAnima
Status
ListedD
ModelExternal source

wan2.1_i2v_480p_scaled_fp8_e4m3_lightx2v_4step_comfyui.safetensors

loraWan 2.1
Status
ListedD
ModelCivitai

彩铅风格_Colored lead style

kohakudelta使用 Kohaku-XL Delta - rev1 | Stable Diffusion Checkpoint | Civitai

loraPony Diffusion
Status
ListedD
ModelExternal source

mage_flow_int8_convrot.safetensors

Models
Status
ListedD
ModelHugging Face

Speaksh Weighted Prompt v1 200

LoRA adapter for speaksh, a local-first natural-language-to-shell command CLI for Unix-like systems.

LoRAmlx-community/MiniCPM5-1B-OptiQ-4bit1B
Status
VerifiedC
ModelCivitai

XL_透明人_Invisible person

不小心删掉了重新传一遍淦( 对应版本用对应的模型

loraSDXL 1.0
Status
ListedD
ModelHugging Face

Distilgpt2 Finetuned Wikitext2

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 3.6141

Otherdistilgpt2
Status
VerifiedC
ModelHugging Face

Vit Resnet Mistral RSICD With 3 Captioning

This model is a fine-tuned version of []( on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.8332 Accuracy: 81.61 Bleu-1: 0.6172 Bleu-2: 0.4856 Bleu-3: 0.3941 Bleu-4: 0.3277...

CLIP vision
Status
VerifiedC
ModelCivitai

Ningguang (Genshin Impact)

Ningguang LoRA 原神の岩元素の★4キャラクター「凝光」のLoRA(LyCORIS)です。 Nigguang from Genshin impact 3種類のLoRAを作成しました。I made 3 LoRAs Original costume Official alternate costume Any costume Trained with animefull-latest

loraStable Diffusion 1.5
Status
ListedD
ModelCivitai

XL_neco-arc

kohakudelta使用 Kohaku-XL Delta - rev1 |稳定扩散检查点 |奇维泰

loraSDXL 1.0
Status
ListedD
ModelCivitai

Lola Metrose (Ore dake Haireru Kakushi Dungeon)

Lola Metrose (Ore dake Haireru Kakushi Dungeon)

loraStable Diffusion 1.5
Status
ListedD
ModelCivitai

XL_Genshin Impact_Lynette_琳妮特

提示词:lingnite cat girl,gray hair,purple eyes,tresshear\(hairstyle)\,capelettequest\(clothing)\,pantyhose,boots,

loraSDXL 1.0
Status
ListedD
ModelCivitai

mcdonald's uniform / 麦当劳小粉

Try size: 768 x 1024 or 1024 x 1024

loraKrea 2
Status
ListedD
ModelExternal source

Qwen-Image-Distill-Q4_K_S.gguf

diffusion_modelQwen-Image
Status
ListedD
ModelCivitai

Goblin Girl Transformation [Anima | Krea 2 | Illustrious | Pony | SD 1.5]

Turns your character into a goblin. This model is mainly trained with female characters, so may not work well with males.

loraStable Diffusion 1.5
Status
ListedD
ModelCivitai

Spirited Away Ghibli Style for Flux

This was an experiment with LoKr for Flux. My best friend in the entire world bghira made this really cool optimizer called adamw schedulefree that's kinda like prodigy but doesn't suck for flux. Using it was like...

loraFLUX.1 [dev]
Status
ListedD
ModelHugging Face

Qwen3.6 27B Heretic ARA GGUF GGUF

This is a decensored version of Qwen/Qwen3.6-27B, made using Heretic v1.2.0 with Magnitude-Preserving Orthogonal Ablation (MPOA). This model is designed for unrestricted, unbound conversational use.

OtherQwen/Qwen3.6-27B
Status
VerifiedC
ModelExternal source

Wan2.2_VAE_bf16.safetensors

vaeWan 2.2
Status
ListedD