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 41,931
Qwen3 30B A3B FP8
This repository contains Qwen/Qwen3-30B-A3B-FP8 together with a Furiosa Executable Bundle (FXB) for running it on FuriosaAI RNGD with Furiosa-LLM. The same model also runs on other frameworks (such as vLLM, SGLang,...
suzukasuraimu | artist style
The weight can be used from 0.1 to 1
Text2ct Weights
Checkpoints for "From Alignment to Synthesis: Contrastive Volumetric Grounding for Text-to-CT Generation" (Molino et al., BMVC 2026).
DizzyIsDizzy Style
Works best at 0.75 weight.
Nene Thomas Style (Anima & Illustrious)
Works best at 0.75 weight.
Lady Kluck (Robin Hood 1973) illustrious
Kluck from 1973 Disney's Robin Hood
Artist Style: swav
The artist style of swav
Dachimotsu Style (Anima & Illustrious)
Works best at 0.75 weight.
Voxtral 4B TTS 2603 TurboQuant MLX 2bit
> [!TIP] > KV-cache quantization without any fork (recommended, 2026): upstream > llama.cpp/Ollama now cover this natively — use -ctk q80 -ctv q80 > (half KV memory, negligible quality loss: perplexity +0.002–0.05)...
Stftvae
Continuous (VAE) neural audio codec built on the STFT. Audio is transformed to a complex spectrogram, a transformer encoder downsamples it to a low-rate continuous latent, and a transformer decoder + ISTFT...
Merger_elle_kitola
Another merger from my TI's
Namaniku Atk Style
Works best at 0.75 weight.
Mizuno Midori/水野翠(for ponyXL)
Trigger cgmzm Basic Prompt black hair,parted bangs,sidelocks,brown eyes Hairstyle(One of the following) ponytail single hair bun Recommended weight 0.6~0.8
xxsha
some style
Wan 2.1 ComfyUI Repackaged
Wan 2.1 repackaged for ComfyUI use. For examples see:
Merger_marily_rose
Another merger from my TI's
narume (pixel art) | Artist Style | GLoRA | ponyXL
Lora trained on pixel art by narume.
VoxCPM2 CoreAI
OpenBMB VoxCPM2 (2B) converted to Apple Core AI, running fully on-device on iPhone (A19 Pro / iPhone 17 Pro) and Mac — no network. The 2B, 48 kHz successor to VoxCPM-0.5B-CoreAI.
HiDream O1 Image FP16
This is the FP16 conversion of HiDream-O1-Image for use with ComfyUI. Weights are stored in float16 — identical memory footprint to BF16 but with a different numerical range, which some GPUs handle slightly differently.
GLM OCR 4bit Mlx
This model was converted to MLX format from zai-org/GLM-OCR using mlx-vlm version 0.6.5. Refer to the original model card for more details on the model.
