# Model Chief > AI models, generative AI and practical ways to build with them. Guides and free project files from the Model Chief YouTube channel. Made by Esha, a Senior AI Developer: "I test generative AI models, build practical workflows and explain how they work." Everything here is free to read and download. Each guide names the software versions it was tested on. ## Guides - [How to make a ComfyUI custom node from scratch](https://modelchief.com/blog/how-to-build-a-comfyui-custom-node/): Make a working ComfyUI custom node in one Python file: the folder, the V3 schema, inputs, outputs and execute, then how to test, debug and share it. - [What is a LoRA? How it works, and how to use one in ComfyUI](https://modelchief.com/blog/what-is-a-lora/): A LoRA is a small file that changes what a big image model does. What's inside one, where it goes in a ComfyUI workflow, and how to set its strength. - [What is ControlNet? How to control the shape of an AI image](https://modelchief.com/blog/what-is-controlnet/): ControlNet makes an image model follow a pose, an outline or a depth map. How it works, which control image to pick, and how to use it in ComfyUI. - [How to install and set up ComfyUI in 2026](https://modelchief.com/blog/how-to-install-comfyui/): How to install ComfyUI on Windows, Linux or Mac: which of the four installs to pick, then models, the Manager, your first image and the day-one errors. - [ComfyUI workflows explained, node by node](https://modelchief.com/blog/comfyui-workflows-explained/): How a ComfyUI workflow runs and what every node in a real FLUX graph does, with renders of each KSampler setting: seed, steps, CFG, sampler and denoise. ## Resources - [AI Image Generation in ComfyUI: The Complete Guide: the files](https://modelchief.com/resources/comfyui-image-generation-guide/): The workflows, prompts and model links from the video. - [Text to image](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/01-text-to-image.json): A prompt in, a picture out. - [Image to image](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/02-image-to-image.json): Starts from a photo. Denoise sets how much of it changes. - [Edit an image](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/03-edit-an-image.json): Changes one thing in a photo from a written instruction. - [Consistent characters](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/04-consistent-characters.json): Puts the same person in a new scene, or turns her into a character sheet. - [Upscale](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/05-upscale.json): Makes the picture four times bigger and saves it. - [Multiple reference images](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/06-multiple-reference-images.json): Four pictures in one edit: her, the dress, the bag and the shoes. - [LoRA](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/07-lora.json): Adds a clay style LoRA to the edit. - [Inpainting](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/08-inpainting.json): Changes only the part you mask. - [Remove objects](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/09-remove-objects.json): Removes whatever you paint over in green. - [Outpainting](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/10-outpainting.json): Extends a picture to the left and right. - [ControlNet: pose](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/11-controlnet-pose.json): Takes the pose from one photo for a new picture. - [ControlNet: depth](https://modelchief.com/downloads/comfyui-image-generation-guide/workflows/12-controlnet-depth.json): Keeps a room's layout and changes its style. - [ComfyUI in 30 Minutes: Complete Beginner Guide (2026): the files](https://modelchief.com/resources/comfyui-complete-beginners-guide/): Everything from the video, free: the two workflows it walks through, the prompt that wrote the custom node, and the node's code. - [Image workflow](https://modelchief.com/downloads/comfyui-complete-beginners-guide/image-workflow-flux-krea.json): The image workflow from the video. Nine nodes turn a written prompt into a 1024 × 1024 photograph, and every one of them has a note beside it saying what it does. Every node ships with ComfyUI, so there's nothing extra to install. - [Video workflow](https://modelchief.com/downloads/comfyui-complete-beginners-guide/video-workflow-wan-2-2.json): The video workflow from the video. It's the same skeleton as the image one with a frame count added, and it makes five seconds of 704 × 1216 video at 24 fps. Every node has a note beside it, and every node ships with ComfyUI. - [Node prompt](https://modelchief.com/downloads/comfyui-complete-beginners-guide/image-picker-prompt.txt): The exact prompt from the video. It went to Claude Code and came back as one complete, working file. The trick is being specific: the node format, every input, the output and the category are all spelled out. - [Node code](https://modelchief.com/downloads/comfyui-complete-beginners-guide/model_chief_image_picker/__init__.py): The complete node from the video. Three image inputs, a dropdown and one output: it passes on whichever image you pick. It's written in ComfyUI's V3 node format, so it needs a recent version of ComfyUI. ## About - [About Model Chief](https://modelchief.com/about/): who makes the guides and how each one is tested ## Optional - [Every guide in full](https://modelchief.com/llms-full.txt) - [YouTube channel](https://www.youtube.com/@themodelchief) - [RSS feed](https://modelchief.com/rss.xml)