LC123 Nodes: <a target="_blank" rel="ugc" href="https://github.com/lonecatone23/ComfyUI_LC123_nodes">https://github.com/lonecatone23/ComfyUI_LC123_nodes</a>LC Vision Nodes: <a target="_blank" rel="ugc" href="https://github.com/lonecatone23/ComfyUI_LC_Vision_nodes">https://github.com/lonecatone23/ComfyUI_LC_Vision_nodes</a>LC note, which is tied to my LC vision pack, will automatically translate to the following languages:<ul><li>English</li><li>中文</li><li>繁體中文</li><li>Русский</li><li>日本語</li><li>한국어</li><li>Français</li><li>Español</li><li>عربي</li><li>Türkçe</li><li>Português (BR)</li><li>فارسی</li><li>עברית</li><li>Italiano</li></ul><hr />Instagram: <a target="_blank" rel="ugc" href="https://www.instagram.com/synth.studio.models/">https://www.instagram.com/synth.studio.models/</a>Buy me a☕ <a target="_blank" rel="ugc" href="https://ko-fi.com/lonecatone">https://ko-fi.com/lonecatone</a>This represents many hours of work that I give away for free. If you enjoy it, Please make sure to 👍like and post to my workflows. That is how you support me!!! Also, feel free to ⚡tip 😉<hr /><h3 id="v2.0">V2.0</h3>So now that I've figured the model out....<ul><li>Built in optimizer settings custom designed for your computer with recommendations</li></ul><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0b6162f8-8e95-48f7-b43d-cecc2d96dd01/original=true/0b6162f8-8e95-48f7-b43d-cecc2d96dd01.jpeg" /><ul><li>Removed unnecessary baggage in the image area like remove background and resize as it didn't work.</li><li>Fixed the issues that every other workflow had with the inferior T2I Images. It now has it's own dedicated encoder</li><li>Minor OCD stuff</li></ul><h3 id="v1.0-beta.">V1.0 Beta.</h3> I ran about 20 workflows and none of them were fast (or good) , so I spent some time figuring it out: What's Included;<ul><li>Options for diffusion and GGUF models</li><li>Optimizers (that work 🤔)<ul><li>Model attention backend</li><li>Qwen image 2.1 Cache (standard)</li><li>EasyCache</li><li>I tried a few other's like Sage, Flash, and Sol, but the results were either negligable or they didn't function</li></ul></li><li>5 step Turbo LoRA options</li><li>Do Image Edit and T2I in the same workflow</li><li>LC vision prompt assist and enhancers</li><li>Multi image options</li><li>VOSR 2.0 Upscaler</li><li>Post Processing</li></ul><h3 id="what-i-found-out-along-the-way:">What I found out along the way: </h3><ul><li>Native node for Image edit and T2I sucks. If this model picks up traction, I'll build better ones<ul><li>There is a bleed across the image inputs that picks up latent data somehow. No clue why</li><li>Still figuring this model out. At one point it was giving me fish gills and deer antlers. It's kinda weird</li></ul></li><li>Turbo LoRA gives decent results, but you really don't save a lot of time</li><li>Qwen 2.1 SUCKS at prompt adherence</li></ul>

Files with SHA256: afbfc92a97e883b81c1a1371af4d9bdd69168f06eb07e1307ed5ee12f60b8de3