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.

Wow I recommend EVERYONE interested in FLUX + LoRAs + Forge watch this. Super comprehensive tutorial on: 1. Getting started with Forge 2. Training LoRA with Fluxgym 3. Using the LoRA 4. Generating a virtual influencer with LoRA 5. Mixing LoRAs And more! I myself learned a lot.

cocktail peanut

35,631 subscribers

78,226 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

14 Comments

cocktail peanut2 years ago

just 14 minutes and literally explains "everything you need to know about flux, forge, and lora"

AiVoiceGuy2 years ago

🙏❤️

cocktail peanut2 years ago

thank you for the video, seriously, i really learned a lot!

AiVoiceGuy2 years ago

Means a lot coming from you! I‘m so grateful and impressed by what you’re doing for this community! Sometimes I can‘t even keep up with trying out the latest tools at the pace you keep adding them to pinokio. Thanks a lot!

EddyLeeKhane2 years ago

@cocktailpeanut Get yourself some X premium Brother More people need to see your work too

AiVoiceGuy2 years ago

@cocktailpeanut Thanks man I‘ll consider it.

Gene Sh2 years ago

Great job on putting together such an informative tutorial! It's clear and covers everything someone needs to get started.

Saba🔺2 years ago

Unfortunately gpu poor, but it's good tutorial :D

Pelayo Arbués2 years ago

@readwise save thread

dude sirwoah2 years ago

I'm unable to use apps in pinochio without the internet. What's up with that?

Lion Dragon2 years ago

How compare to Astria consistent character trainnjng ?

Kyle ✌🏻❤️2 years ago

Would this video still be useful for someone looking to create LoRAs in other softwares (Draw Things on iOS) with other models (Stable Diffusion XL)? I just can’t find very much online for LoRA creation in general

index.html2 years ago

if you want to learn - don't use pinokio.

txh2 years ago

does it allow controlnet use?

Related Videos

Fluxgym: Train FLUX LoRA LOCALLY with LOW VRAM FLUX LoRAs are super exciting, but there has not been an easy way to train them LOCALLY using LOW VRAM machines. Fluxgym is a Gradio app for training your own Flux LoRAs on your own 12G, 16G, 20G+ VRAM computer for free.

Fluxgym: Train FLUX LoRA LOCALLY with LOW VRAM FLUX LoRAs are super exciting, but there has not been an easy way to train them LOCALLY using LOW VRAM machines. Fluxgym is a Gradio app for training your own Flux LoRAs on your own 12G, 16G, 20G+ VRAM computer for free.

cocktail peanut

237,915 views • 2 years ago

🎨 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

12,794 views • 3 months ago

I Built an open source virtual try-on professional LoRA at fal Lora for Flux Klein 9b Edit, give it a photo of someone + 2 clothing items and it dresses them up Works with men and women, all kinds of outfits Weights are open on HuggingFace, and there's a playground you can try right now

I Built an open source virtual try-on professional LoRA at fal Lora for Flux Klein 9b Edit, give it a photo of someone + 2 clothing items and it dresses them up Works with men and women, all kinds of outfits Weights are open on HuggingFace, and there's a playground you can try right now

Lovis Odin

15,494 views • 7 months ago

As I promised yesterday, I'll briefly explain LoRA training and share a workflow I made so you can do it quickly. First, let me answer a very common question: 'Why train LoRAs when we have such advanced models?' Even though we have incredibly advanced models now (like NBP), we still can't always get them to do specific things we want. Simplest example: the spritesheet LoRA I made the other day. I generated 1000 images with Nano Banana and only 100 were what I wanted. The LoRA I trained using those 100 images gives me nearly 100% consistent results. Second point is cost and speed. With LoRA, we can cut costs by 4-5x. And while doing that, we're generating 4-5x faster. How many images do you need for a good LoRA? This depends on your LoRA's complexity. For example, when I training the spritesheet LoRA, even though I used 100 images, I didn't include buildings in the training data, so this LoRA doesn't work for buildings. So think about your LoRA's use cases and add examples for as many use cases as possible to improve quality. What are paired images and how to train LoRAs for image-editing? When training LoRAs for image editing on fal, we call each edit example paired images - one with _start suffix, one with _end suffix. For example, if you're training a background remove LoRA, the unedited original photo will be your '_start' image. The image with background removed will be the '_end' image. Simply put: images we want to edit or use as reference get _start, target images we want to achieve get '_end'. Important: save both images with the same name. Like image332_start.jpg and image332_end.jpg. This way the system knows which images pair together. What about training LoRAs for models with multiple image inputs? Same logic. We still use _start and _end suffixes, but with one difference. Since there are multiple input images, we can number them: _start, _start1, _start2. Example: start images, 1st image = Woman portrait (image35_start.jpg) 2nd image = Glasses photo (image35_start1.jpg) 3rd image = Hat photo (image35_start2.jpg) Output image = portrait of woman wearing glasses and hat (image35_end.jpg) Can we do more detailed captioning? Yes. Similarly, you can improve training quality by creating a txt file for each set with the caption inside. Example: create image35.txt and write: 'Recreate the image by putting the glasses from the second image and the hat from the third image on the woman in the first image.' What are Steps? How many should I use? What's Learning Rate? Steps determines how many times the model sees and processes your training data (your images). Each step, the model learns a bit more. But as steps increase, so does the risk of overfitting. So there's no real default. But for a simpler LoRA with 20 paired images, 1000 steps is ideal. Here's a metaphor for the Steps and Learning Rate relationship: Imagine you have a balloon. Our goal is to inflate it to the optimal size. Steps = How many times we blow into the balloon Learning rate = How hard we blow each time If we blow too softly, we need to blow many more times. If we blow too hard, we risk popping it quickly and can't reach optimal size. Of course training won't explode, but it won't work as intended because it wasn't trained optimally. Training's done, now what? Once training's complete, you'll have a safetensors file. Every model you train on fal has a LoRA inference endpoint. In that inference, add your safetensors file link to the LoRA url input, and you can use your LoRA. Thanks for the read! The workflow in the video: If I forgot anything, let me know in the replies.

As I promised yesterday, I'll briefly explain LoRA training and share a workflow I made so you can do it quickly. First, let me answer a very common question: 'Why train LoRAs when we have such advanced models?' Even though we have incredibly advanced models now (like NBP), we still can't always get them to do specific things we want. Simplest example: the spritesheet LoRA I made the other day. I generated 1000 images with Nano Banana and only 100 were what I wanted. The LoRA I trained using those 100 images gives me nearly 100% consistent results. Second point is cost and speed. With LoRA, we can cut costs by 4-5x. And while doing that, we're generating 4-5x faster. How many images do you need for a good LoRA? This depends on your LoRA's complexity. For example, when I training the spritesheet LoRA, even though I used 100 images, I didn't include buildings in the training data, so this LoRA doesn't work for buildings. So think about your LoRA's use cases and add examples for as many use cases as possible to improve quality. What are paired images and how to train LoRAs for image-editing? When training LoRAs for image editing on fal, we call each edit example paired images - one with _start suffix, one with _end suffix. For example, if you're training a background remove LoRA, the unedited original photo will be your '_start' image. The image with background removed will be the '_end' image. Simply put: images we want to edit or use as reference get _start, target images we want to achieve get '_end'. Important: save both images with the same name. Like image332_start.jpg and image332_end.jpg. This way the system knows which images pair together. What about training LoRAs for models with multiple image inputs? Same logic. We still use _start and _end suffixes, but with one difference. Since there are multiple input images, we can number them: _start, _start1, _start2. Example: start images, 1st image = Woman portrait (image35_start.jpg) 2nd image = Glasses photo (image35_start1.jpg) 3rd image = Hat photo (image35_start2.jpg) Output image = portrait of woman wearing glasses and hat (image35_end.jpg) Can we do more detailed captioning? Yes. Similarly, you can improve training quality by creating a txt file for each set with the caption inside. Example: create image35.txt and write: 'Recreate the image by putting the glasses from the second image and the hat from the third image on the woman in the first image.' What are Steps? How many should I use? What's Learning Rate? Steps determines how many times the model sees and processes your training data (your images). Each step, the model learns a bit more. But as steps increase, so does the risk of overfitting. So there's no real default. But for a simpler LoRA with 20 paired images, 1000 steps is ideal. Here's a metaphor for the Steps and Learning Rate relationship: Imagine you have a balloon. Our goal is to inflate it to the optimal size. Steps = How many times we blow into the balloon Learning rate = How hard we blow each time If we blow too softly, we need to blow many more times. If we blow too hard, we risk popping it quickly and can't reach optimal size. Of course training won't explode, but it won't work as intended because it wasn't trained optimally. Training's done, now what? Once training's complete, you'll have a safetensors file. Every model you train on fal has a LoRA inference endpoint. In that inference, add your safetensors file link to the LoRA url input, and you can use your LoRA. Thanks for the read! The workflow in the video: If I forgot anything, let me know in the replies.

ilker

15,192 views • 8 months ago

🚨 Training Flux LoRAs is the hottest trend in AI-enabled visual content. Check out this 4-min video where we guide you through training custom Flux models on #Scenario, making perfectly consistent characters with ease. The smoothest UI and workflow in the industry. YT link 📺 in the next post.

🚨 Training Flux LoRAs is the hottest trend in AI-enabled visual content. Check out this 4-min video where we guide you through training custom Flux models on #Scenario, making perfectly consistent characters with ease. The smoothest UI and workflow in the industry. YT link 📺 in the next post.

Emm | scenario.com

18,693 views • 2 years ago

I'm going to try and upload the last two videos I shot with Lora Cross and Goddess Phoenix Sinz in december 2024 on loyalfans. The first video was Double Cross'd (1/2)

I'm going to try and upload the last two videos I shot with Lora Cross and Goddess Phoenix Sinz in december 2024 on loyalfans. The first video was Double Cross'd (1/2)

OTSEddy

13,377 views • 7 months ago

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 ⬇️

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 ⬇️

ComfyUI

12,761 views • 22 days ago

Doc-to-LoRA: What if you could online distill documents into your LLM weights without training? 🚀 Stoked to share our new work on instant LLM adaptation using meta-learned hypernetworks 📷📝 Building on our previous Text-to-LoRA work, we doc-condition a hypernetwork to output LoRA adapters, improving the base LLM's effective context window. The hypernetwork is meta-trained on 1000s of summarization tasks and shows remarkable compression capabilities at low latency 📈 🧑‍🔬 Work led by Rujikorn (Tan) Charakorn with Edoardo Cetin & Shin Useka at Sakana AI 📷

Doc-to-LoRA: What if you could online distill documents into your LLM weights without training? 🚀 Stoked to share our new work on instant LLM adaptation using meta-learned hypernetworks 📷📝 Building on our previous Text-to-LoRA work, we doc-condition a hypernetwork to output LoRA adapters, improving the base LLM's effective context window. The hypernetwork is meta-trained on 1000s of summarization tasks and shows remarkable compression capabilities at low latency 📈 🧑‍🔬 Work led by Rujikorn (Tan) Charakorn with Edoardo Cetin & Shin Useka at Sakana AI 📷

Robert Lange

37,390 views • 7 months ago

Kingdom Come 2’s new House Building mechanic is seriously impressive with its forge So much more customization than I anticipated, All I wanted was a real home for Henry and this forge DLC is everything I could’ve asked for

Kingdom Come 2’s new House Building mechanic is seriously impressive with its forge So much more customization than I anticipated, All I wanted was a real home for Henry and this forge DLC is everything I could’ve asked for

Synth Potato🥔

63,081 views • 1 year ago

Google Veo3 creates beautiful base videos, but what if that’s not enough? I built a ComfyUI workflow that takes it further: 🏗 New structure with Flux (LoRA arch) 📦 Turned into 3D with Hunyuan3d 2 🔁 Integrated + relight via Flux, Controlnet, Denoise and Redux 🎞️ Finalized the video using Wan2.1 + CausVid + VACE The result? Custom, controllable, cinematic videos far beyond the original VEO3. ⚠️ There are still a few scale and quality issues I'm currently working on, but the core process is solid. 📹 I’ll drop a full video tutorial next week. 📁 In the meantime, you can download the workflows, links in the comments (I am using a H100 for it, but probably a A100 is enough).

Google Veo3 creates beautiful base videos, but what if that’s not enough? I built a ComfyUI workflow that takes it further: 🏗 New structure with Flux (LoRA arch) 📦 Turned into 3D with Hunyuan3d 2 🔁 Integrated + relight via Flux, Controlnet, Denoise and Redux 🎞️ Finalized the video using Wan2.1 + CausVid + VACE The result? Custom, controllable, cinematic videos far beyond the original VEO3. ⚠️ There are still a few scale and quality issues I'm currently working on, but the core process is solid. 📹 I’ll drop a full video tutorial next week. 📁 In the meantime, you can download the workflows, links in the comments (I am using a H100 for it, but probably a A100 is enough).

Lovis Odin

89,083 views • 1 year ago

Character LoRA on Flux – sneak peak 👀 I trained a model on 15 character images (same pose, different expressions) and now I can generate endless variants in new setups and poses. One image per inference, perfect consistency (both style + subject) with over 90% usable straight out of the box. Video below 👇 Trained on Scenario today.

Character LoRA on Flux – sneak peak 👀 I trained a model on 15 character images (same pose, different expressions) and now I can generate endless variants in new setups and poses. One image per inference, perfect consistency (both style + subject) with over 90% usable straight out of the box. Video below 👇 Trained on Scenario today.

Emm | scenario.com

48,818 views • 2 years ago

Trained a voice lora on Walken using just 6 clips as a test to see how well VoxCPM handles learning a voice. Then I just did audio + image = video with LTX 2.3. This TTS model feels extremely powerful, fully open sourced (Apache 2.0) More below 👇

Trained a voice lora on Walken using just 6 clips as a test to see how well VoxCPM handles learning a voice. Then I just did audio + image = video with LTX 2.3. This TTS model feels extremely powerful, fully open sourced (Apache 2.0) More below 👇

A.I.Warper

24,253 views • 5 months ago

I trained this LTX LTX 2.3 LoRA of George Costanza at home on my 5090 in about a day with AI Toolkit. I generated this 30 second video with ComfyUI on my 5090 in 6 minutes. Open source is, always has been, and always will be, the future of generative AI. (SOUND ON)

I trained this LTX LTX 2.3 LoRA of George Costanza at home on my 5090 in about a day with AI Toolkit. I generated this 30 second video with ComfyUI on my 5090 in 6 minutes. Open source is, always has been, and always will be, the future of generative AI. (SOUND ON)

Ostris

395,312 views • 6 months ago

LLava just hit 3800 stars on Github. It's a multimodal Large Language-and-Vision Assistant that can understand images and text. LLava can even handle memes (the same ones GPT-4 demo'ed at launch) and set a new SOTA on Science QA. It also supports LLaMA-2, LoRA training with academia GPUs, higher resolution (336x336), 4-/8- inference.

LLava just hit 3800 stars on Github. It's a multimodal Large Language-and-Vision Assistant that can understand images and text. LLava can even handle memes (the same ones GPT-4 demo'ed at launch) and set a new SOTA on Science QA. It also supports LLaMA-2, LoRA training with academia GPUs, higher resolution (336x336), 4-/8- inference.

Lior Alexander

143,540 views • 3 years ago