by Harmeet | Jan 26, 2026 | Tutorial
Its been a while since I jumped into the AI Toolkit by Ostris and there are so many new models that have been released. So I decided to jump back into it to train my Desi Babes (for flux) on Z-Image Turbo using the toolkit. My default setup for running this is to go...
by Harmeet | Jan 11, 2026 | ComfyUI
All this is a newly trained VAE for Flux.1 which has been trained on high resolution 4k images. This means that when you generate large images of 4k resolution using Flux.1 this model VAE decoder will produce a higher quality results that the native VAE provided by...
by Harmeet | Dec 13, 2025 | ComfyUI
If your ComfyUI workflows are starting to look like spaghetti, subgraphs are about to become your best friend. In this guide, I’ll walk you through how to take a cluttered workflow and convert it into a neat, reusable subgraph. This not only tidies up your canvas but...
by Harmeet | Dec 7, 2025 | General
Z Image Turbo is bringing something back which was getting lost with some of the newer models like Flux.2 Dev, Wan 2.2, Qwen Image…the ability to run it locally! Of course some of these other models have quantized version available but that’s so far...
by Harmeet | Nov 9, 2025 | ComfyUI
If you’ve ever wanted to take an existing photo and make it look like it was captured from a completely different angle, the new Qwen Edit 2509 Multi Angle LoRA is going to help you with that. This LoRA has been designed specifically for multi-angle editing, allowing...
by Harmeet | Oct 23, 2025 | ComfyUI, Resources
Qwen Image Edit and Image Edit 2509 are two very versatile model that holds the power to photo editing like never before. As showcased in some of the past videos its super simple to setup locally and use with simple prompts. If you want to learn how to prompt I...
by Harmeet | Oct 10, 2025 | ComfyUI
QWEN Image Edit model which is designed to replace many different tools we’ve used like Inpainting, outpainting, controlnet, LoRA and its newest yet most powerful feature in context image editing with simple text prompts. No need for masks or segmentation, just...
by Harmeet | Sep 20, 2025 | General
Flux is a great model, don’t get me wrong but there is one thing that gives flux a bad name which is the plastic skin and the flux chin. The fix had been to train and use various different LoRAs to enhance the skin but in my experience many of them work well...
by Harmeet | Aug 8, 2025 | Resources
SeedVR2 is an upscaler model by ByteDance-Seed for Video Restoration and is licensed under Apache-2.0 license. This implies that can be used in commerical capacity if you want. The one thing to note is that this model is GPU VRAM hungry model and you will struggle to...
