Find what you need for your workflow.

Diives Style

Works best at 0.75 weight.

Obsidian Anise

V2 Update : V2 tones down the lineart and adds more depth through shading, color, texture, and lighting. It can handle both clean 2D anime and a more semi-real finish while keeping a clear manga/anime base.

Roscoe Style

Works best at 0.75 weight

Puchidori Style

Works best at 0.75 weight.

Vit Base Oxford Iiit Pets

This model is a fine-tuned version of google/vit-base-patch16-224 on the pcuenq/oxford-pets dataset. It achieves the following results on the evaluation set: Loss: 0.2032 Accuracy: 0.9486

Dpt Beit Large 384

The Intel/dpt-beit-large-384 model is based on Monocular depth estimation with the BEiT backbone. Monocular depth estimation, aiming to infer detailed depth from a single image or camera view, finds applications in...

(Video Tutorial Resources) SkyReels, Quick Flux Text Fixes, Flux Gradients are back! — v1.0

KEY COMFY & STABLE DIFFUSION TOPICS

Luztapiaart Style

Works best at 0.75 weight.

Immiland Style

Works best at 0.75 weight.

Kristallion Style

Works best at 0.75 weight.

Aubergrin Style (Anima & Illustrious)

Works best at 0.75 weight.

Merger_kyra_rebling

Another merger from my TIs

Onyx Kokoro 82M

A mixed-precision MLX quantization of Kokoro-82M (StyleTTS2-derived, Apache-2.0), packaged for Onyx — an on-device iOS AI assistant. Used by OnyxTTS, Onyx's own from-scratch Swift + MLX text-to-speech engine, to...

Maxsun YuanJia(铭瑄瑗珈形象)

Here is the translation of your text:

Matsuda Arisa/松田亜利沙(for ponyXL)

Trigger mlmar Basic Prompt brown hair,twintails,brown eyes Recommended weight 0.6~0.8

Irodori Warabi Style

Works best at 0.75 weight.

Merger_meg_esprie

another merger from my TIs

Tandohark Style (Anima & Illustrious)

Works best at 0.75 weight.

comfyui-signed-image

SIGNEDIMAGE - a zero-centered counterpart to ComfyUI's IMAGE - plus conversion and preview nodes.

林雨霞 明日方舟 Lin Arknights