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 30,523
Savage Sands 12B MPOA GGUF
For a convenient overview and download list, visit our model page for this model.
Llama3.1 8B Sudo Sft 5epochs Forget10mix600 1sft 2sft
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on an unknown dataset.
Specter Tenebria (Dark Tyrant) - Epic Seven
Donations appreciated if you like my work!
Qwen3 4B Chemical GRPO TR
This repository contains the Qwen3-4B Chemical GRPO batch-size-32 run. The repository name uses the requested GRPO-TR suffix, but the actual training method for this checkpoint is GRPO.
steps_150000_pytorch_model.pt
RedCraft | 红潮2 | 赤佬3 INT8/INT4/FP8 Scaled 加速
OpenRS GRPO
This model is a fine-tuned version of Qwen/Qwen3.5-0.8B on the knoveleng/open-rs dataset. It has been trained using TRL.
[SDXL] Artist Style: Xerganea
v8.340 -> v8.3402: Fixed mosaic censoring issue
Gemma 4 E2B It ARA Heresy GGUF
For a convenient overview and download list, visit our model page for this model.
Sylvanas Windrunner (World of Warcraft) - Cinematic Version
Krea 2 version might be a bit rough around the edges, but hey! I'm still learning. Her armor is a bit hard to get rid of sometimes.
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-Q5_K_M.gguf
The Vexations of a Shut-In Vampire Princess (Hikikomari Kyuuketsuki no Monmon ひきこまり吸血姫の悶々) || Terakomari Gandesblood / Villhaze / Karen Helvetius / Sakuna Memoir / ...
The updated LoHa is in bundle format and it can only be used on webui version >= 1.7.0
wdxl-aesthetic-0.9.safetensors
4x-UltraSharpV2.safetensors
Xournalpp Htr Word Detector
A word-detection model that locates individual handwritten words in document images. It produces axis-aligned bounding boxes — no transcription or labels. Part of the Xournal++ HTR project.
Deepseek Ocr2 Chart v1
This model is a fine-tuned version of deepseek-ai/DeepSeek-OCR-2 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.6978
Yulya SmolLM2 135M
> The smallest model in the Yulya family — a 135M-parameter conversational AI experiment designed to bring Yulya's expressive and chaotic personality to extremely lightweight local AI applications.
Dan Mumford Inspired Style XL
Experimental model of Dan Mumford Style.
Change-A-Character: Female Samurai, You Waifu Now Follows The Bushido Code!
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...
