New nodes – IAMCCS_nodes: Updated version 1.3.1
I’ve just released a new update to IAMCCS_nodes, my custom node suite for ComfyUI, focused on real-world cinematic video generation.This update introduces IAMCCS WanImageMotion, a new node designed to fix a critical issue in long-form video workflows based on SVI Pro. When using LoRAs in SVI Pro pipelines, motion often collapses into artificial slow motion.This […]
When Cinema Thinks Through Form: Anamorphic imperfection and generative cinema
Hi folks, this is CCS. I’m a filmmaker first — not a technologist who discovered cinema later.Alongside my film work (including my first feature film Sometimes in the Dark, other info here on my website), I’ve been conducting hands-on research in AI-cinema and generative film language, working directly on models, workflows and optical behavior (as […]
Cinema Before Theory
Sometimes in the Dark and the Origin of an Optical Question (this post is the second part from my previous one hosted here and on patreon (www.patreon.com/IAMCCS) I didn’t start thinking about optical imperfection while writing a paper. I started thinking about it when the image began to resist me. Sometimes in the Dark (check […]
Coming soon Paper following up concept LoRA
We’re proud to present You the excerpt of our paper following up the concept LoRA “Anamorph1x”, a LoRA based on Z-IMAGE model simulating the anamorphic cinematic style. Here the excerpt: “Contemporary generative image systems increasingly equate visual quality with total visibility: ultra-high resolution, uniform sharpness, noise suppression, and spatial coherence. In parallel, streaming distribution has […]
🎥 NEW WORKFLOWS — Qwen-VL Face Swap + Enhanced Qwen Edit simple v.2 (with LoRA Support for Low VRAM)
Hi friends, IAMCCS here — and today I’m releasing two new workflows for Qwen Image Edit 2509, both deeply integrated with the Prompt Enhancer and the upgraded IAMCCS_nodes tools. This post expands and updates my previous posts and pushes it into a fully working release with: ✓ A Face Swap Workflow (v1.0.1) ✓ A Qwen […]
UPDATE IAMCCS CUSTOM NODES! — New Prompt Enhancer v1.0.1 + Massive IAMCCS_nodes 1.3.0 Upgrade
Hi folks, this is CCS, and today we’ve got a double-upgrade drop — two huge updates to the tools powering your Qwen and WAN workflows: ➜ IAMCCS_QE_PROMPT_ENHANCER v1.0.1 👉 https://github.com/IAMCCS/IAMCCS_QE_PROMPT_ENHANCER ➜ IAMCCS_nodes v1.3.0 (major update) 👉 https://github.com/IAMCCS/IAMCCS_nodes This is the kind of update that doesn’t just “fix things”…It makes your entire pipeline smarter, quicker, and […]
LET’S TRY QWEN IMAGE EDIT 2509 WITH OUR NEW CUSTOM NODES!
Hi folks, this is IAMCCS, and today we’ll dive into the real thing — the acclaimed model from Alibaba, Qwen Image Edit 2509, working side-by-side with our new custom nodes: IAMCCS_QE_Prompt_Enhancer and my little baby, IAMCCS_annotate! We’ll use models like the Nunchaku version and the normal diffusers (with a deeper dive into the Nunchaku installation […]
Two brand-new CUSTOM NODES for ComfyUI — IAMCCS_annotate & IAMCCS_QE_Prompt_Enhancer!!
Hi folks, this is IAMCCS. I’ve been working on something special for you. Today I’m going to show you two brand-new utilities just released after the acclaimed IAMCCS_nodes pack. These tools aren’t ordinary nodes — they’re creative extensions for the way you think and work inside ComfyUI. As a thank you to my Patreon community, […]
IAMCCS_nodes: NEW VERSION 1.2.3 IS HERE!
I’m really happy to announce that the new version of the Custom Node for ComfyUI is finally here!After so many requests, I’ve updated our amazing node that allows you to load LoRAs directly inside native workflows (no WAN wrapper needed) and load character LoRAs ad LightX2V ones — including the latest models based (from WAN […]
New! IAMCCS Native WAN 2.2 Animate Workflow – plus IAMCCS-node (Lora fix) and Long video!
Hi folks, this is CCS, and today I’m sharing a new native workflow for WAN 2.2 Animate — extended, refined, and made stable for everyone who’s been struggling with the “LoRA key not loaded” problem. Many of you have run into it: LoRAs simply refuse to load inside native WAN workflows.They only seemed to work […]