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 42,193
ラスティアラ・フーズヤーズ/ Lastiara Whoseyards 異世界迷宮の最深部を目指そう(Let's Aim for the Deepest Part of the Otherworldly Labyrinth)
Can use followed prompt to suppor t generate : yellow eyes, blonde hair, very long hair
[PonyV6 XL LoCon] Fake MrBeast | Meme
Trigger + Additional Tag: fakemrbeast, hands up
My OC - Georgia [IllustriousXL]
Reviews, Hearts, Likes etc. are very appreciated!
shiratori aira (Dandadan) [ponyXL]
A lora trained off of art of shiratori aira from Dandadan
[PonyXL] Selen Tatsuki/セレン龍月/龙月Selen-彩虹社/Nijisanji/にじさんじ Vtuber
High frequency word: selen tatsuki:1.00,head wings:1.00,heterochromia:0.84
Yvonne WAI Illustrious LoRA (DoRA)
This DoRA is trained on Yvonne , a character from Arknights: Endfield .
Retro 80 anime embedding (Illustrious)
→ Get it now for much cheaper prices, skip the wait:
Andrea Horowitz MXAI
Andrea's a lovely girl who doesn't exist.
Sensei | No longer Allowed In Another World
Works best at 0.85 weight, Pony works best at 0.75 weight.
Lizette Gieselmann MXAI
Lizette was trained on 62 AI prompted images.
Flux + Jasper AI ControlNets + LoRAs — v1.0
Super simple workflow that combines Jasper AI ControlNet + Flux LoRAs.
SD 1.5: Fixer Ti Set (Negative Embeddings) - SupaColdShower
These are Fixer TI's like AntiChild, DrafterNeg etc - now including a BARELY working Bad hands negative version.
Qwen3.6 27B GGUF
> [!IMPORTANT] > This model is automatically converted using
Gemma 4 31B It NVFP4
See Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks.
Gemma 4 12B It Assistant BF16
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.
Owlv2 Large Patch14 Finetuned
The OWLv2 model (short for Open-World Localization) was proposed in Scaling Open-Vocabulary Object Detection by Matthias Minderer, Alexey Gritsenko, Neil Houlsby. OWLv2, like OWL-ViT, is a zero-shot text-conditioned...
Elizabeth from Bioshock: Infinite [IllustriousXL]
! I'm not training specific outfits !
WAS Boris Vallejo and Julie Bell
W AS Boris Vallejo and Julie Bell
Deepfake Audio Wav2vec2
Deepfake-Audio-Wav2Vec2 is a fine-tuned audio classification model trained to detect real vs spoofed (deepfake) speech audio.
Moshika Rag Candle BF16
MoshiRAG is a compact full-duplex speech language model augmented with asynchronous knowledge retrieval to improve factuality without sacrificing real-time interactivity. Built on top of Moshi, MoshiRAG predicts when...
