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 35,000
[IllustriousXL v0.1 LoCon] Jagoda Jęczyduch / Baba Yaga | Awaria
This is a requested character.
Qwen3 ASR 1.7B Q4 0 GGUF
A 4-bit (Q40) GGUF quantization of Qwen3-ASR 1.7B, for use with llama.cpp's audio-multimodal path (llama-server / llama-mtmd-cli).
Highschool DxD Style
Works best at 0.75 weight.
FoodEntityRecognition BioBERT Frozen Layers v4
This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.0042 Precision: 0.8063 Recall: 0.8747 F1: 0.8391 Accuracy: 0.9869
Kate (Child) | Shadows House
Works best at 0.95 weight.
Aki (Girls Frontline)
Someone said to someone "NOT ENOUGH DATA" - Well clearly they hadn't met me.
Typhoon Whisper Turbo Mlx
An MLX (Apple Silicon) conversion of typhoon-ai/typhoon-whisper-turbo — SCB 10X's Thai fine-tune of OpenAI Whisper large-v3-turbo (800M params). float16 weights, ready for mlx-whisper.
Merger_ruby_marhime
another merger from my TI's
Merger_veronica_danneth
another merger
Okashira Moppu Style
Works best at 0.75 weight.
Zounose Style (Anima & Illustrious)
Works best at 0.75 weight.
Lvface Weights
This repository is a preservation mirror of the released LVFace ONNX embedding weights for use with the lvface Python package.
XL Kobayakawa Sae/小早川纱枝/小早川紗枝 Idolmaster/偶像大师
Base Model: Animagine XL V3.1
TRELLIS Image Large
The image conditioned version of TRELLIS, a large 3D genetive model. It was introduced in the paper Structured 3D Latents for Scalable and Versatile 3D Generation.
Qwen3.6 27B Heretic Uncensored FINETUNE NEO CODE Di IMatrix MAX GGUF
Ultimate: Exceeds Qwen 3.6 27B performance, uncensored and NEO-Di-Matrix quants to bring all that power in quant form. Q4/IQ4s clock in at 94% of full precision (BF16), with Q6 at just under 98%. Even IQ2M : 83% of...
LongCat Image Edit Turbo DF11
For more information (including how to compress models yourself), check out and
Queen Chrysalis | My Little Pony: Friendship Is Magic
Works best at 0.75 weight.
Vietnam | Hetalia
Works best at 0.95 weight.
KAIROS MM Qwen2.5 VL 7B SFT GGUF AIO GGUF
> KAIROS-MM-Qwen2.5-VL-7B-SFT is a multimodal reasoning model based on Qwen2.5-VL, designed to enable robots and vision AI agents to reason about the real world using physics understanding, prior knowledge, and...
Mika Pikazo Style
Trained on NoobAI-XL
