Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch 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 38,600
ControlNet SD XL 1.0 Depth Zeed
These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with new type of conditioning. You can find some example images below. prompt: a fairy princess made of glass, glowing runes etched...
Hechima Style
Works best at 0.95 weight.
Shining Nikki/闪耀暖暖 Style
Trained on NoobAI-XL
ControlNet
Can be used in sd-webui-controlnet. Put the yaml file with model because it is sd2.1 vprediction model.
XL Totoki Airi/十时爱梨/十時愛梨, Idolmaster/偶像大师
Base Model: Animagine XL V3.1
Teefer333 Style
Works best at 0.75 weight.
Rino Cnc Style
Works best at 0.75 weight.
Diyokama Style
Works best at 0.75 weight.
[PonyV6 XL LoCon] Ariake | Kantai Collection
This is a requested character.
Wan 2.1 ComfyUI Repackaged
Wan 2.1 repackaged for ComfyUI use. For examples see:
My Beauty Vit
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.0062 Pearson: 0.8867 Mse: 0.0062
Qwen3 Vl 4b Vision Encoder
> [!Important] This is the vision encoder component of the Qwen-3VL-4B-Instruct model. For more details, please visit the original model page or refer to the Qwen-VL technical reports published by Qwen.
Pepshi506 Style
Works best at 0.75 weight.
HTRP Báiyáo
character of my own creation
Sapiens Depth 0.3b
Sapiens is a family of vision transformers pretrained on 300 million human images at 1024 x 1024 image resolution. The pretrained models, when finetuned for human-centric vision tasks, generalize to in-the-wild...
Realiusart Style
Works best at 0.75 weight.
[Anima] Artist Style: yaungpeng
lora for anima-base1.0 trigger words: `@yaungpengStyle`
Gemma 4 E4B It Sdnq Dynamic 8bit
This is an int8 quantized version of google/gemma-4-E4B-it using SDNQ (SD.Next Quantization) with the dynamic option, Hadamard Rotation and quantized embeddings.
VAM_mckenzie_rose
another VAM creation
Ddpm Anime Faces 64
ddpm-anime-faces-64 is an educational project for introducing the training and sampling processes of DDPM and DDIM models. The model is trained on huggan/anime-faces dataset.
