#ComfyUI

KugelAudio — Open‑Source 7B‑Parameter TTS (ComfyUI‑Compatible)

Text‑to‑Speech covering 24 European languages with voice cloning. An open‑source model that outperformed ElevenLabs in the authors’ A/B tests.

I looked into VNCCS, a ComfyUI tool that auto-generates character sheets

I investigated VNCCS, a character-sprite generation suite for visual novels, and its QWEN Detailer utility. Can it help generate side twin-tails more reliably?

Can Z-Image run on RunPod? I checked it for character consistency

I looked into whether Alibaba Tongyi-MAI's Z-Image can produce stable manga-style character art without breaking the design, using RunPod and ComfyUI.

RunPod setup for Qwen-Image-Layered LoRA

Configuration for running a Qwen-Image-Layered LoRA that automatically separates facial parts on RunPod. Comparison of RTX 6000 Ada (48GB) and RTX PRO 6000 (96GB).

Qwen-Image-Edit NSFW on RunPod: RTX 4090 failures, RTX 5090 success, and 3-view reference sheets

Hands-on RunPod log for Qwen-Image-Edit NSFW using Phr00t AIO: why my RTX 4090 attempt failed, what worked on RTX 5090, and how I used it to create 3-view reference sheets for a 3D model base mesh.

Qwen-Image-Edit-2511 on RunPod: working ComfyUI setup, Multi-Angle LoRA (96 viewpoints), ~¥3 per image at $0.34/hr

Setup notes for Qwen-Image-Edit-2511 on RunPod's RTX 4090 ($0.34/hr) using the ComfyUI template. Includes the fal Multiple-Angles LoRA (4 elevations × 8 azimuths × 3 distances) and a per-image cost breakdown that ends up cheaper than buying a 4090.

Setting Up LLM/RAG for Work, So I Tried LoRA Training on the Side (Part 1)

Introducing a Mac mini M4 Pro to build an in-house RAG system. A plan for setting up a LoRA training environment during downtime while waiting for specs to be finalized.