Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

ComfyUI Tutorial for Beginners: LoRAs, Style Transfer & ControlNets Module 3 is where you stop pulling the lever and start directing. Prompt iteration gets you close. These are the tools that get you exactly where you wanted to land. Style, structure, and pose, set before the sampler ever runs.... What you'll learn: → How a LoRA attaches to a base model to change its output without retraining it → Why a LoRA has to match its base model family, and where to find them on Comfy Hub and Civitai → Model strength vs. CLIP strength — two dials, two different jobs → Stacking multiple LoRAs at different weights until the style is yours → Training your own: dataset, trigger word captions, step count, TrainLoRA locally → Reading the plot loss graph instead of guessing whether it worked → Appending to a LoRA you've already trained → Style transfer two ways: denoise-driven img2img vs. IP-Adapter reading style straight off a reference → ControlNets with DWPose, Depth Anything V2, and canny — composition locked before the prompt is read → Side by side: what each control map actually preserves → Fixing weak LoRAs, overcooked stacks, mismatched preprocessors, and noisy transfers Click the links below to run the workflow ⬇️show more

ComfyUI

57,858 subscribers

12,761 views • 2 months ago •via X (Twitter)

Arts Science & Technology Education

Anya Rossi• Live Now

Private livecam show

7 Comments

Qtum.ai2 months ago

48 minute video. I wonder if I can finish this before another major AI release happens.

ComfyUI2 months ago

Stay tuned!

Olivier Heckendorn2 months ago

Where are all the tutorials ??

ComfyUI2 months ago

Our YT:

ComfyUI2 months ago

Run the workflow:

bee2 months ago

Doug can you help me with this one. I put the melon wedge in nano banana and asked it for a rectangular chisel. Got a Result in seconds. Can i do the same comfy and zimage turbo ? i need a way to control where the chisel will be and in what shape. So far nothing comes close

Marc2 months ago

Good breakdown; for video gen in the same setup, running Wan 2.2 at Q4 with 4 steps and no LoRA already gets clean 576x976 output before you even touch base model weights, worth testing that baseline first.

Related Videos

🎨 I trained 999 Style LoRAs with the fal Krea 2 Trainer. Every single image in this video is a different LoRA. That's 999 unique Style LoRAs, each trained for just 100 steps at 0.00035 LR, taking an average of ~30 seconds to train. As I said before, Krea 2 continues to prove that it's an incredible model for open-source Style LoRAs. Next week I'll be sharing even more LoRAs, along with a few surprises.

🎨 I trained 999 Style LoRAs with the fal Krea 2 Trainer. Every single image in this video is a different LoRA. That's 999 unique Style LoRAs, each trained for just 100 steps at 0.00035 LR, taking an average of ~30 seconds to train. As I said before, Krea 2 continues to prove that it's an incredible model for open-source Style LoRAs. Next week I'll be sharing even more LoRAs, along with a few surprises.

ilker

13,060 views • 4 months ago

ComfyUI Tutorial for Beginners: Text-to-Image & Image-to-Image Workflows One graph, two workflows and Module 2 is where you build it node by node instead of loading someone else's. We start from a blank canvas and wire every connection, then change a single value and turn the same graph into image-to-image. What you'll learn: → The 5 core nodes, connected one at a time — checkpoint, CLIP encode, KSampler, empty latent, VAE decode → Why the data flows the way it does, not just where the wires go → Every KSampler setting: seed, steps, CFG, sampler, scheduler → Denoise from 0.9 to 0.0 — the one value that decides how much of your source survives → Locking seeds and generating takes instead of chasing one perfect image → Preview vs. save, and why every image carries the graph that made it → Reopen any result in your asset library as a live workflow → The 6 errors that break Comfy most often → How to read a red node like a sentence Click the links below to run the workflow ⬇️

ComfyUI Tutorial for Beginners: Text-to-Image & Image-to-Image Workflows One graph, two workflows and Module 2 is where you build it node by node instead of loading someone else's. We start from a blank canvas and wire every connection, then change a single value and turn the same graph into image-to-image. What you'll learn: → The 5 core nodes, connected one at a time — checkpoint, CLIP encode, KSampler, empty latent, VAE decode → Why the data flows the way it does, not just where the wires go → Every KSampler setting: seed, steps, CFG, sampler, scheduler → Denoise from 0.9 to 0.0 — the one value that decides how much of your source survives → Locking seeds and generating takes instead of chasing one perfect image → Preview vs. save, and why every image carries the graph that made it → Reopen any result in your asset library as a live workflow → The 6 errors that break Comfy most often → How to read a red node like a sentence Click the links below to run the workflow ⬇️

ComfyUI

61,630 views • 2 months ago

ComfyUI Tutorial for Beginners: Full Node Graph Basics It's a production-grade generation backend with an adaptable front end and Module 1 is where the node graph stops being intimidating. We boot up Comfy Cloud, tour the full UI, and build your first workflow from the ground up. What you'll learn: → Comfy Cloud vs. Desktop - which to use and when → Navigating the graph: pan, zoom, frame, select → The 5 core nodes behind every text-to-image workflow → Checkpoints, LoRAs, VAEs, CLIP - matching model versions → Get/Set nodes + reroutes to kill the spaghetti → Subgraphs: complex workflows collapsed into one node → App Mode: a front end for non-technical collaborators → Templates vs. Blueprints vs. Workflows → The 7 node categories that make the whole library click No installs. No missing models. Open it and generate.

ComfyUI Tutorial for Beginners: Full Node Graph Basics It's a production-grade generation backend with an adaptable front end and Module 1 is where the node graph stops being intimidating. We boot up Comfy Cloud, tour the full UI, and build your first workflow from the ground up. What you'll learn: → Comfy Cloud vs. Desktop - which to use and when → Navigating the graph: pan, zoom, frame, select → The 5 core nodes behind every text-to-image workflow → Checkpoints, LoRAs, VAEs, CLIP - matching model versions → Get/Set nodes + reroutes to kill the spaghetti → Subgraphs: complex workflows collapsed into one node → App Mode: a front end for non-technical collaborators → Templates vs. Blueprints vs. Workflows → The 7 node categories that make the whole library click No installs. No missing models. Open it and generate.

ComfyUI

15,034 views • 2 months ago

ComfyUI for Animation: Concept Art to Any Angle Concept art → 3D proxy → any angle you want. One graph, two methods. Step 1: load your concept art. Tripo generates a 3D model and saves it as a GLB. Drag it into Load 3D and set material mode to Normal. Step 2 (stills): rotate the viewport to your angle. Load 3D outputs the view, and GPT Image 2 renders it back as a polished on-style illustration. Step 3 (camera moves): record a path in the viewport. That clip becomes the motion reference for Seedance 2.0, which generates the move through the stylized scene. Click the link below to run the workflow ⬇️

ComfyUI for Animation: Concept Art to Any Angle Concept art → 3D proxy → any angle you want. One graph, two methods. Step 1: load your concept art. Tripo generates a 3D model and saves it as a GLB. Drag it into Load 3D and set material mode to Normal. Step 2 (stills): rotate the viewport to your angle. Load 3D outputs the view, and GPT Image 2 renders it back as a polished on-style illustration. Step 3 (camera moves): record a path in the viewport. That clip becomes the motion reference for Seedance 2.0, which generates the move through the stylized scene. Click the link below to run the workflow ⬇️

ComfyUI

42,720 views • 1 month ago

MOSS-Image is now supported in ComfyUI @OpenMOSS dropped an open-weight image model that has blown up across the community. It’s a 5B model that renders legible text, accepts structure layout prompts and has a high bar for aesthetics. The community has already been cooking up finetunes and LoRAs while the Comfy team has been working to support the model to run seamlessly on any consumer hardware. This model is a must try - check it out.

MOSS-Image is now supported in ComfyUI @OpenMOSS dropped an open-weight image model that has blown up across the community. It’s a 5B model that renders legible text, accepts structure layout prompts and has a high bar for aesthetics. The community has already been cooking up finetunes and LoRAs while the Comfy team has been working to support the model to run seamlessly on any consumer hardware. This model is a must try - check it out.

ComfyUI

23,451 views • 22 days ago

MOSS Image dropped less than a week ago and it’s already at 1.29M downloads on Hugging Face. If you have consumer hardware, this open source image model is for you + FREE workflow below → 5B params → int8 weights are only 5.4GB → Apache 2.0 license → seamless install via Comfy Desktop The quality punches way above it's weight. Great work by OpenMOSS. What the ComfyUI community shipped in 5 days: → color + depth control adapter (darask0) → hires LoRA, native 4096×2304 gens (thee comfyanonymous) → LoRA training support all the major tools → Kromoss finetune, with a 8step DMD2 turbo LoRA (lodestones) → DSLR realism LoRA (Danrisi) I built a workflow for the color-depth control adapter running in ComfyUI. Prompt adherence and detail is spot on (check the lens flare).

MOSS Image dropped less than a week ago and it’s already at 1.29M downloads on Hugging Face. If you have consumer hardware, this open source image model is for you + FREE workflow below → 5B params → int8 weights are only 5.4GB → Apache 2.0 license → seamless install via Comfy Desktop The quality punches way above it's weight. Great work by OpenMOSS. What the ComfyUI community shipped in 5 days: → color + depth control adapter (darask0) → hires LoRA, native 4096×2304 gens (thee comfyanonymous) → LoRA training support all the major tools → Kromoss finetune, with a 8step DMD2 turbo LoRA (lodestones) → DSLR realism LoRA (Danrisi) I built a workflow for the color-depth control adapter running in ComfyUI. Prompt adherence and detail is spot on (check the lens flare).

rob - comfyui

14,490 views • 20 days ago

Comfy API is live Point it at a workflow JSON and it handles the rest: → Resolves your custom nodes, models, LoRAs, and Python deps → Pins it all, ComfyUI version included, into a versioned Build → Cuts an immutable release, so what you test is what ships → Deploys as an autoscaling endpoint on RTX PRO 6000, H100, H200, or B200 Click the link below to deploy your first workflow and learn more with our blog ⬇️

Comfy API is live Point it at a workflow JSON and it handles the rest: → Resolves your custom nodes, models, LoRAs, and Python deps → Pins it all, ComfyUI version included, into a versioned Build → Cuts an immutable release, so what you test is what ships → Deploys as an autoscaling endpoint on RTX PRO 6000, H100, H200, or B200 Click the link below to deploy your first workflow and learn more with our blog ⬇️

ComfyUI

9,615,313 views • 1 month ago

MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability MiniMax (official) leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. Download the workflows & learn more in our blog 👇

MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability MiniMax (official) leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. Download the workflows & learn more in our blog 👇

ComfyUI

235,460 views • 3 months ago

MiniMax H3 is the SOTA open weight model... but the large model comes with slow gens (depending on your hardware). You can be waiting for minutes just for the generation to miss the mark Here's a ComfyUI workflow to get the most out of H3 without the wait. → H3 Turbo LoRA (4–8 steps) → Model Preview Override + Tiny AutoEncoder H3 for a fast composition preview → Bad preview? stop it, tweak the prompt or seed → Save your precious gpu time Workflow and model links below 👇

MiniMax H3 is the SOTA open weight model... but the large model comes with slow gens (depending on your hardware). You can be waiting for minutes just for the generation to miss the mark Here's a ComfyUI workflow to get the most out of H3 without the wait. → H3 Turbo LoRA (4–8 steps) → Model Preview Override + Tiny AutoEncoder H3 for a fast composition preview → Bad preview? stop it, tweak the prompt or seed → Save your precious gpu time Workflow and model links below 👇

rob - comfyui

26,990 views • 3 months ago

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Santiago

84,747 views • 2 years ago

$QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.$

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino 🤖

43,075 views • 6 months ago

Today we're launching three new LoRAs for our open source video model, LTX Video! 🕺 Pose LoRA 🏞️ Depth LoRA ✏️ Canny LoRA Get unprecedented control over your AI videos and train new control types with just a few samples on consumer hardware. Details below 👇

Today we're launching three new LoRAs for our open source video model, LTX Video! 🕺 Pose LoRA 🏞️ Depth LoRA ✏️ Canny LoRA Get unprecedented control over your AI videos and train new control types with just a few samples on consumer hardware. Details below 👇

LTX.io

140,253 views • 1 year ago

Exploring a new storyboard format: Depth Map Storyboards. Instead of letting Seedance 2.0 inherit the storyboard's visual style, I used a reference image to define the tone and look, while the depth-map storyboard defines the composition and camera framing. workflow + system prompt below 🧵

Exploring a new storyboard format: Depth Map Storyboards. Instead of letting Seedance 2.0 inherit the storyboard's visual style, I used a reference image to define the tone and look, while the depth-map storyboard defines the composition and camera framing. workflow + system prompt below 🧵

OAK

80,362 views • 3 months ago

Big day for open source. MiniMax Music 3 is undeniably a state of the art open weights Music Generation model and a real alternative to Suno. My favorite part about open weights: the best is yet to come. Once the community starts playing with the model and training LoRAs, this model only gets better and allows for more control.

Big day for open source. MiniMax Music 3 is undeniably a state of the art open weights Music Generation model and a real alternative to Suno. My favorite part about open weights: the best is yet to come. Once the community starts playing with the model and training LoRAs, this model only gets better and allows for more control.

rob - comfyui

324,397 views • 2 months ago

Being the eldest daughter is such a beautifully dark storyline to live out layered in strength, sorrow, pressure, and power. You learned how to read a room before you knew how to read a book. You became the role model, the trial run, the secret keeper. But there comes a day where you get to release it all.

Being the eldest daughter is such a beautifully dark storyline to live out layered in strength, sorrow, pressure, and power. You learned how to read a room before you knew how to read a book. You became the role model, the trial run, the secret keeper. But there comes a day where you get to release it all.

𝕭𝖗𝖚𝖏𝖆♡𝕭𝖎𝖙𝖈𝖍 | Witchy Astrologer

215,540 views • 1 year ago

LoRA training is the standout feature. You can fine tune Qwen Image directly online, export the trained LoRA, and plug it straight into ComfyUI workflows like any custom model. This replaces a lot of paid LoRA setups.

LoRA training is the standout feature. You can fine tune Qwen Image directly online, export the trained LoRA, and plug it straight into ComfyUI workflows like any custom model. This replaces a lot of paid LoRA setups.

SANI BULA

15,462 views • 9 months ago

The open source community has been delivering on LTX 2.3 LoRAs. Fine tuning LTX 2.3 unlocks control that you can't get from closed models. Here are 7 LoRAs that can save your footage. There are too many incredible LoRAs to cover, so comment below your favorite that needs a showcase! Links to all the workflows below 👇

The open source community has been delivering on LTX 2.3 LoRAs. Fine tuning LTX 2.3 unlocks control that you can't get from closed models. Here are 7 LoRAs that can save your footage. There are too many incredible LoRAs to cover, so comment below your favorite that needs a showcase! Links to all the workflows below 👇

ComfyUI

232,870 views • 5 months ago

how to use for free. step by step. 1. open 2. hit Market in the nav bar. or click Explore Free Systems in the hero. or tap See the Build on any featured system. all three take you to the same place. 3. pick any system. you will see two options: > option A: get the files. full codebase, resources, customization guide, and a video walkthrough showing exactly how to set it up and use it. this is the paid route, everything in one place, nothing to figure out. > option B: get the prompt and doc. the exact prompt and documentation to replicate the system yourself. free. experiment with it, break it, rebuild it, make it yours. 4. there is also a free prompt skill attached to most systems. this gives you the style and structure so you can generate your own version of the website or workflow using any model you already have access to. 5. if you are a subscriber, you get the Start Build button. it connects directly to Claude and GPT so you can run the system inside motionwiki without switching tabs or copying prompts manually. 6. save any system to your library for later. come back to it when the project needs it. that is the full loop. find the system, get the prompt free, build it yourself, or get the full files if you want it done faster.

how to use for free. step by step. 1. open 2. hit Market in the nav bar. or click Explore Free Systems in the hero. or tap See the Build on any featured system. all three take you to the same place. 3. pick any system. you will see two options: > option A: get the files. full codebase, resources, customization guide, and a video walkthrough showing exactly how to set it up and use it. this is the paid route, everything in one place, nothing to figure out. > option B: get the prompt and doc. the exact prompt and documentation to replicate the system yourself. free. experiment with it, break it, rebuild it, make it yours. 4. there is also a free prompt skill attached to most systems. this gives you the style and structure so you can generate your own version of the website or workflow using any model you already have access to. 5. if you are a subscriber, you get the Start Build button. it connects directly to Claude and GPT so you can run the system inside motionwiki without switching tabs or copying prompts manually. 6. save any system to your library for later. come back to it when the project needs it. that is the full loop. find the system, get the prompt free, build it yourself, or get the full files if you want it done faster.

MotionViz

12,023 views • 3 months ago