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 41,940
NullStyle-no.5-rurudo
对NOOBAI-eps-1.0的rurudo画风增强,无触发词,推荐权重1
DreamVAE
A distilled decoder for the ACE-Step 1.5 Oobleck VAE. Drop-in replacement: same [B, 64, T] latent input, same [B, 2, 1920T] stereo output at 48 kHz. 51.7M parameters (61% of the teacher), 0.24 dB SNR degradation vs....
PS3 Lang 4K SigLIP2
PS3Lang-4K-SigLIP2 is a vision encoder that extracts visual features from images of up to 4K resolution.
Inputwo Style for NoobAI
如有要求,将予以删除 Will remove if requested
Merger_ayla_lenore
Another merger
Cosmos3 Nano GPTQ 4bit
Cosmos3-Nano-GPTQ-4bit is a 4-bit GPTQ-quantized version of NVIDIA/Cosmos3-Nano, designed for deployment on consumer hardware with reduced VRAM requirements.
Yokotn Style
Works best at 0.95 weight.
Lhata Style
Works best at 0.75 weight.
Huihui Qwen3 VL 2B Instruct Abliterated 8bit Mlx
This model was converted to MLX format from huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated using mlx-vlm version 0.6.5. Refer to the original model card for more details on the model.
Huihui Qwen3 VL 2B Instruct Abliterated 4bit Mlx
This model was converted to MLX format from huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated using mlx-vlm version 0.6.5. Refer to the original model card for more details on the model.
Frisk | Undertale
Works best at 0.75 weight.
Yukimura821 Style
Works best at 0.75 weight.
setanta(Fate)
因为网上开放下载的模型要付费所以自己练了一个自娱自乐。 瑟坦特(Fate) 示例图片似乎被civitai屏蔽了,由于我目前基础模型更换到noobai, 对此无能为力
IS Net Anime
IS-Net-Anime is a deep learning model designed to provide interactive image segmentation capabilities. The model allows users to refine segmentation masks through user interactions, making it highly effective for...
Gemma 4 E2B It Ultra Uncensored Heretic MLX 5bit Int5 Affine
This model was converted to MLX from llmfan46/gemma-4-E2B-it-ultra-uncensored-heretic using mlx-vlm version 0.6.3. Please refer to the original model card for more details.
Gemma 4 12B It Assistant 6bit
This model was converted to MLX format from google/gemma-4-12B-it-assistant using mlx-vlm version 0.6.0. Refer to the original model card for more details on the model.
Gemma 4 E2B It Uncensored Heretic Ara MLX 6bit Int6 Affine
This model was converted to MLX from p-e-w/gemma-4-E2B-it-heretic-ara using mlx-vlm version 0.6.3. Please refer to the original model card for more details.
DeepSeek R1 NVFP4 v2 Mlpinf
This model is a quantized version of DeepSeek AI's DeepSeek R1 model, produced with the official NVIDIA TensorRT Model Optimizer DeepSeek recipe and calibrated with the MLPerf Inference deepseek-r1 calibration...
Qwen Image Edit Causal
We employ block causal attention to improve inference speed of Qwen-Image-Edit-2511.
Znkn4524 Style
Works best at 0.75 weight.
