20 shown - 348 total matches
Turn any video into a perfect lip-synced talking masterpiece. Who it's for: creators who want this pipeline in ComfyUI without assembling nodes fro...
Basically, it generates in low resolution first and then finishes at the original resolution. It uses just the basic latent upscale, so it's a bit ...
Anima Turbo + CFG 1 Negative prompt A lightweight, beginner-friendly workflow for Anima Turbo that allows negative prompting at CFG 1 using NegPip ...
A very simple image to prompt workflow.
Model repo on Hugging Face Hub.
Okay, This straight up is the coolest thing I've seen in a while. Thansk to What Dreams Cost for this insane set of nodes With this node you can cr...
ℹ️ Babes Kissable Lips 5.0 marks a new direction for the model, bringing it closer to its roots. It features an artistic digital style characterized by a unique visage and proportions. This high-gloss digital portrait model delivers luminous, light-reactive skin and exceptional clarity of detail. It renders characters with a polished, almost crystalline quality - smooth surfaces that catch and reflect light beautifully, creating a sense of depth and vibrancy under dramatic lighting.<br /><br />The model excels at expressive facial rendering, particularly in the eyes and lips, which are depicted with refined shapes, subtle textures, and a strong visual presence. Hair is rendered with rich color, volume, and reflective highlights, while the overall aesthetic blends semi-realistic grounding with stylized elegance, resulting in portraits that feel both intimate and cinematic.<br /><br />Its strength lies in vibrant color work, intricate material rendering, and atmospheric lighting. Whether placed against clean gradients, cosmic scenes, or stylized environments, the model consistently produces images with an interesting, cohesive visual language and a strong sense of crafted beauty.<br />
FLUX Power LoRA + ControlNet + Face Detailer (Simple) A clean and beginner-friendly FLUX workflow focused on realistic character generation. After ...
<p><strong>ZED IMAGE TURBO - Technical Specifications</strong></p><p><strong>🎨 Generation Parameters</strong></p><p><strong>Model Configuration:</strong></p><ul><li><p><strong>Model:</strong> FZIT_0605FP16 (cf727ea834)</p></li><li><p><strong>Base Architecture:</strong> neo-2.22</p></li><li><p><strong>Precision:</strong> float8-e5m2 (fp16 LoRA)</p></li><li><p><strong>VAE:</strong> zImage_vae</p></li><li><p><strong>Text Encoder:</strong> zImage_textEncoder</p></li></ul><p><strong>Sampling Settings:</strong></p><ul><li><p><strong>Sampler:</strong> DPM++ 2s a RF</p></li><li><p><strong>Schedule:</strong> KL Optimal</p></li><li><p><strong>Steps:</strong> 9</p></li><li><p><strong>CFG Scale:</strong> 1</p></li><li><p><strong>Shift:</strong> 9</p></li><li><p><strong>Denoising Strength:</strong> 0.3</p></li><li><p><strong>RNG Source:</strong> CPU</p></li></ul><p><strong>Resolution & Upscaling:</strong></p><ul><li><p><strong>Base Size:</strong> 1024x1536</p></li><li><p><strong>Hires Upscale:</strong> 2x (4x-UltraSharp)</p></li><li><p><strong>Final Output:</strong> ~2048x3072</p></li><li><p><strong>Hires Steps:</strong> 9</p></li><li><p><strong>Hires Shift:</strong> 9</p></li><li><p><strong>Hires CFG:</strong> 1</p></li></ul><p><strong>⚡ Performance Metrics</strong></p><p><strong>Generation Time:</strong> 3 min. 45.1 sec</p><p><strong>Memory Usage:</strong></p><ul><li><p><strong>Active VRAM:</strong> 17.37 GB</p></li><li><p><strong>Reserved VRAM:</strong> 17.53 GB</p></li><li><p><strong>System RAM:</strong> 19.1/24 GB (79.8%)</p></li></ul><p><strong>🔧 Hardware Requirements</st...
Changes the way you approach LTX genning. LTX doesn't adhere to prompts well, so stop beating your head on the wall trying to prompt better. Instea...
flux-1-dev-non-commercial-license
Model repo on Hugging Face Hub.
<p>Join The Tinkerer on <a target="_blank" rel="ugc" href="https://whop.com/joined/cyberdelia-ai-lab/products/the-tinkerer/">Whop</a> to download this model and many more — all for one monthly payment. Plus, get early releases, private tools <strong>and</strong> a lot more.<br />👉 <a target="_blank" rel="ugc" href="https://whop.com/joined/cyberdelia-ai-lab/products/the-tinkerer/">Join on Whop</a><br /><br />New direction, new behavior. Enhanced detail, cleaner, improved prompt response, and more stable results across a wide range of generations.<br /><br />All examples are <strong>100% LoRA-free</strong> and generated with Forge Neo.</p><p>If your results aren’t quite what you expected, take a quick step back and check a few things first:<br />– Did I stack a bunch of LoRAs?<br />– Am I using a lot of Textual Inversions?<br />– Is my prompt actually structured well?</p><p>In most cases, it’s not the checkpoint causing the issue 🙂</p>
``` OPTIMIZED - minimal VRAM _ Max quality balance 🎧 ULTIMATE_WAN2.2-TripTrap-v11-ENDLESS-or-LOOP-Workflow 🎧 Experimental Pop / Glitch Artist &...
Ideogram-v4 workflow + Json prompts based on: https://blog.comfy.org/p/ideogram-4-day-0-support-in-comfyui { "high_level_description": "", "style_d...
Reed Anima T2I Workflow
Create
<h3 id="i.-introduction"><strong>I. Introduction</strong></h3><p><strong>AnimaYume</strong> is a <strong>text-to-image</strong> model fine-tuned from <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima"><strong>Anima</strong></a>, a high-quality anime-style image generation model developed by <a target="_blank" rel="ugc" href=...
flux-1-dev-non-commercial-license
flux-1-dev-non-commercial-license
I just made a new Telegram Group and Discord group drop in for chats, questions, feedbacks or just to share your work. 欢迎加入 纸飞机 和 Discord 群组。 RH体验地...
