Lessons

Learn mode holds 79 built-in lessons in 12 groups, and after them the group My lessons with the lessons you make or import. This chapter has one page per built-in lesson, in the order of the list in the app.

#What Learn mode is

In Learn mode you build real graphs by hand on the canvas while the app leads you step by step: what to do, why, where it is on the canvas. It sees from the canvas when a step is done. No assistant model is needed. Lessons use only the nodes your ComfyUI has, and they never download model files: you bring those to ComfyUI yourself. How it all works: How lessons work.

A lesson card may say that the lesson goes on from another one. That is a hint, not a lock: any lesson can be started on its own.

#The lessons by group

#ComfyUI basics

• How ComfyUI works: lesson "comfy-basics". You learn what a graph, the queue and the models folder are, and find a node, an output and a model file yourself.
• Reading someone else's workflow: lesson "read-workflow". You learn to read groups, notes, reroutes, primitives, Set and Get, bypassed nodes and subgraphs, and give two fields one value.
• When the graph does not fit the graphics card: lesson "vram". You learn why a graph runs out of memory and what to change, and set the picture graph up to need less of it.

#Pictures: first steps

• A first picture from text: lesson "image". You build a graph of seven nodes that draws a picture from a prompt.
• The prompt: how a model reads it: lesson "prompt". You learn what a model does with text and how to steer a picture with words.
• The sampler's settings: lesson "sampler-fields". You set the fields of the sampler the way ComfyUI's own SDXL template sets them, and learn what each one does.
• Refining with a second model: lesson "refine". A second model redraws a finished picture: the composition comes from the first, the texture and style from the second.

#Video

• Video from text: lesson "video-text". You build a Wan 2.2 graph that makes a five-second clip from a prompt.
• A prompt for video: lesson "prompt-video". You learn to describe a clip so that the model understands the motion and the camera.
• Video from a picture: lesson "video-image". You bring a finished picture to life: it becomes the first frame of the clip.
• LoRA: add a style or a subject: lesson "lora". You connect a LoRA to both models and put its words into the prompt.
• Fast video in four steps: lesson "video-fast". You cut twenty steps down to four with a speed-up LoRA.
• Two models in one graph: lesson "two-models". A picture model draws the first frame and Wan brings it to life. Each has its own LoRAs and its own prompt.
• Video on a modest graphics card: Wan 2.2 5B: lesson "video-small". You build a one-model Wan 2.2 graph that makes a five-second 720p clip from a prompt, or from an image.
• When a video does not fit in memory: lesson "video-memory". You change the graph of the small Wan model so that it needs less graphics memory, and you know what each change costs.
• Video guided by another video: Wan 2.2 Fun Control: lesson "video-control". Your image comes to life with the motion of another video: its depth, its pose or its edges.
• A portrait that speaks: HuMo: lesson "video-speech". A person from an image says the words of a sound file, with ComfyUI's own nodes, no pack.
• Video with sound: LTX-2.5: lesson "video-ltx". One run draws a clip and its sound together, from a prompt.
• Video from text: HunyuanVideo 1.5: lesson "video-hunyuan". You build the HunyuanVideo 1.5 graph with a custom sampler and get a five-second 720p clip.
• Video from text: Kandinsky 5 Lite: lesson "video-kandinsky". You build a light one-model graph that makes a five-second clip from a prompt.
• Smoother motion: more frames between frames: lesson "video-interpolate". A finished clip gets twice as many frames and plays smoothly at twice the frame rate.

#WanVideoWrapper

• Video on WanVideoWrapper: lesson "wrapper". You build a Wan 2.2 graph on the nodes of the WanVideoWrapper pack and see how it differs from the built-in one.
• Video from a picture on WanVideoWrapper: lesson "wrapper-image". A clip made on WanVideoWrapper nodes starts from your picture.
• VACE: motion from another video: lesson "wrapper-vace". A clip on WanVideoWrapper repeats the motion, the depth or the outlines of another video.
• Animation by pose: Wan Animate: lesson "wrapper-animate". The character from your picture repeats the moves and the face of the person in a video.
• Animation by pose: UniAnimate: lesson "wrapper-unianimate". The character from a picture repeats the moves of a person in a video. A Wan 2.1 model and one LoRA are enough.
• A talking video: InfiniteTalk: lesson "wrapper-talk". A portrait says the words of a sound file, the lips in time with them.
• Two people talking: InfiniteTalk: lesson "wrapper-duo". Two people in one picture speak, each with their own voice.
• A talking portrait: FantasyTalking: lesson "wrapper-fantasy". A portrait says a short voice recording. The graph is simpler than InfiniteTalk's, the clip shorter.
• A video with sound: Ovi: lesson "wrapper-ovi". One run draws the clip and its sound at once: the character's speech, steps, street noise.
• Another camera: ReCamMaster: lesson "wrapper-recam". A finished video is drawn again as if the camera had moved another way.

#Pictures: models

• SDXL done properly: lesson "sdxl". You set an SDXL graph to the size and the settings the family was trained for.
• Pony and Illustrious: tags instead of sentences: lesson "tags". You write a tag prompt with the quality words of the model's page and set the size and sampler such models are used with.
• Choosing a sampler and a scheduler: lesson "samplers". You put two samplers side by side that differ in one setting only, and learn to choose by comparing.
• Which loader for which file: lesson "loaders". You find the right loader for four kinds of model files and learn where ComfyUI looks for each.
• Flux.1: a picture from separate files: lesson "flux". You build a Flux graph of ten nodes, where the model, the two text encoders and the VAE come from loaders of their own.
• Z-Image Turbo: a picture in eight steps: lesson "zimage-turbo". You build a graph for a distilled model that draws in 8 steps with cfg 1, and learn why its negative prompt does nothing.
• Qwen-Image: words inside the picture: lesson "qwen-image". You build a Qwen-Image graph with a real negative prompt, the shift of the family and its own size.
• Flux.2 Klein: a sampler built from parts: lesson "flux2-klein". You build the graph of a small Flux.2 model, where the sampler is put together from five nodes.
• SD 3.5: one file and a new empty latent: lesson "sd35". You build an SD 3.5 graph from one checkpoint with the empty latent and the settings of this family.
• A quantised model: GGUF: lesson "gguf". You put a GGUF model into a graph of separate files, so a large model fits a smaller video card.

#Video: the anchor picture

• The start picture is the anchor: lesson "anchor-start". Your picture becomes the first frame of the clip, and you know how to trade motion for likeness.
• Two anchors: first and last frame: lesson "video-flf". You give two images, and the model draws the clip that goes from the first to the last.
• A reference for the whole clip: Wan VACE: lesson "anchor-reference". A person or an object from your picture stays itself in every frame, not only in the first.
• A longer video in parts: lesson "anchor-parts". Two parts of a clip join through a shared anchor frame into one longer video.

#Packs and tools

• Load, cut and save video: VideoHelperSuite: lesson "video-vhs". You load a piece of a video at a chosen frame rate and save it with its sound.
• A larger, sharper video: SeedVR2: lesson "video-upscale". A low-resolution clip is redrawn at 1080p with its details restored.
• Remove an object from a video: ProPainter: lesson "video-remove". An object marked by a mask video disappears, and the background behind it is filled in from the neighbouring frames.
• ControlNet from a depth map: lesson "controlnet-depth". The comfyui_controlnet_aux pack turns a picture into a depth map, and the model draws a new scene in the same space.
• A reference picture with IP-Adapter: lesson "ipadapter". An SD 1.5 or SDXL model takes the style of a sample picture through the ComfyUI_IPAdapter_plus pack.
• Fixing faces and hands with a detailer: lesson "detailer". The Impact Pack finds the faces in a finished picture and draws each one again at a larger size, so small faces come out sharp.
• Two versions of a prompt with one switch: lesson "switch". You keep two prompts in one graph and choose between them with one yes/no value, the way ComfyUI's templates do.
• A language model writes the prompt: lesson "llm-prompt". You let a language model inside ComfyUI turn a short idea into a detailed prompt, and compare it with your own by the switch.

#Pictures: techniques

• A picture from a picture: lesson "img2img". A picture you already have becomes a new one: the same composition, drawn again by the model as the prompt says.
• Inpainting: redraw part of a picture: lesson "inpaint". You paint a mask over part of a picture, and the model draws only that part again, by a new prompt.
• Outpainting: a picture beyond its edges: lesson "outpaint". A picture gets a new strip on one side, and the model draws what lies beyond the frame.
• A mask by words: lesson "mask-text". ComfyUI finds an object by its name and gives its mask to the inpainting node, with no painting by hand.
• Upscaling with a model: lesson "upscale". The finished picture is enlarged by a model that draws sharp detail instead of stretching the pixels.
• A second pass after upscaling (hires fix): lesson "hires-fix". The enlarged picture is drawn once more by the model: sharp detail at a size the model cannot draw in one go.
• ControlNet: drawing along the edges of a picture: lesson "controlnet". The model draws a new picture that keeps the outlines of a sample picture.
• LoRA for pictures: lesson "lora-image". Two LoRAs in a chain change the style and the subject of a picture model, each with its own strength.
• LoRA for a character: face, body, clothes, pose: lesson "lora-character". Three LoRAs on one picture, each tuned on its own, the face kept while a body or clothing LoRA works.
• Editing a picture by words: lesson "edit-words". A model made for editing changes a picture as an instruction says: "make the sofa green", "remove the cup".
• A reference picture for style (Flux Redux): lesson "style-reference". A Flux.1 picture takes its look from a sample picture: colours, materials, mood.
• Removing a background: lesson "remove-background". A picture whose background is made transparent, saved as PNG.

#Sound and speech

• Music from text: ACE-Step 1.5: lesson "audio-music". You build a graph that writes a song from a list of styles and your lyrics.
• A sound from text: Stable Audio: lesson "audio-sound". You build a graph that makes a sound effect or a short piece of music from a prompt.
• Speech from text: Chatterbox: lesson "audio-speech". You build a graph that reads your text aloud in the voice of a short recording.
• Sound for a silent video: MMAudio: lesson "audio-foley". You build a graph that listens to the frames of a silent clip and gives it a sound in time with them.
• Speech to text: Whisper: lesson "audio-transcribe". You build a graph that writes down what is said in a recording and saves subtitles.

#3D

• A picture into a 3D model: Hunyuan3D 2: lesson "3d-image". You build a graph that turns one picture of an object into a 3D model you can open in other programs.

#Faces and characters

• The same character in a new picture: FLUX.1 Kontext: lesson "character-kontext". You build a graph that draws your invented character again, in a new place or pose, with the same face and clothes.
• One character in many pictures: lesson "character-series". You learn what holds a character's identity and practise a new pose and new clothes while the face stays.
• The same face from one photo: IP-Adapter FaceID: lesson "face-same-photo". You add IP-Adapter FaceID to the first picture graph so that a photo of a face drives the face of the new picture.
• Put a face onto a picture: ReActor: lesson "face-swap". You build a graph that puts a face from one picture onto a person in another picture you already have.
• Restore a face in an old picture: ReActor: lesson "face-restore". You build a graph that redraws blurred or damaged faces in a picture with a face restoration model.

#For adults (18+)

Closed until the switch Adult content (18+) in Settings ▸ Privacy is on. Technique in general words for lawful adult (18+) work with consent; see Content rules.

• Pictures for adults: what changes: lesson "adult-image". You learn what the content of a picture depends on and check your graph.
• Adult LoRAs: how to load and balance them: lesson "adult-lora". You load your own LoRA, check which model it fits and learn to balance two LoRAs.
• Video for adults: what changes: lesson "adult". You learn what the content of a clip depends on and check your graph.

#My lessons

• My lessons: make a lesson from a graph, try it, save it, import and export lessons.
• The lesson file format: what a .lesson.json file holds.

#About the lessons

• How lessons work: choosing, following, Show me where, Do this for me, the next lesson.

For the ideas behind each step, read ComfyUI concepts.

#See also

• Home
• Learn mode
• The lessons panel