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 38,781
Prefect Illustrious XL v15 SDXL
faipl-1.0-sd
Nova Anime XL Il v80 SDXL
faipl-1.0-sd
Prefect Illustrious XL v3 SDXL
faipl-1.0-sd
Qwen3.6 35B A3B Abliterated v4 GGUF
license: apache-2.0 basemodel: Bahushruth/Qwen3.6-35B-A3B-abliterated-v4 tags: abliteration uncensored qwen3 moe gguf llama-cpp ollama modeltype: qwen3moe pipelinetag: text-generation datasets:...
PiD INT8 (flux1_512_2048_INT8)
Works with Zimage/Turbo and Flux1 (or any flux1 vae model)
Cosmos Predict2 2B t2i
Note: gallery is actually create using the fp8 version: because I cannot make this version run on tensor dot art
Hassaku XL Illustrious v21 SDXL
faipl-1.0-sd
Huihui Ornith 1.0 9B Abliterated MTP GGUF
This is an uncensored version of deepreinforce-ai/Ornith-1.0-9B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove...
Ltx 2 2.3 I2V Nsfw Furry Multi Purpose Sex LoRA
Base model: LTXV 2.3 Trained words:
Wan 2.2
You will find here all the Wan 2.2 video models used with WanGP (https://github.com/deepbeepmeep/Wan2GP) :
Evolai Mb2 002
Sabor Latino v1
SABOR LATINO - Illustrious / SDXL
svdq-int4_r64-ernie-image
This adds W4A4 quantized inference support for ERNIE Image Turbo to Nunchaku, delivering significant speedup and memory reduction with minimal quality loss.
Qwen3.6 35B A3B Heretic GGUF
HiDream-O1-Image_clear_v1
Guide (External site): English | Japanese
Qwen3.6 27B PARO
Qwen3.5 4B PARO
SuimeiXL-Illustrious
Boogu Official Comfy-Org Checkpoints
Make sure you have ComfyUI version 0.27.0 or newer installed to have the latest INT8 support/fixes.
