| This is a training of a public LoRA style (4 seperate training each on 4x A6000). | |
| Experimenting captions vs non-captions. So we will see which yields best results for style training on FLUX. | |
| Generated captions with multi-GPU batch Joycaption app. | |
| I am showing 5 examples of what Joycaption generates on FLUX dev. Left images are the original style images from the dataset. | |
| # I used my multi-GPU Joycaption APP (used 8x A6000 for ultra fast captioning) | |
| # https://www.patreon.com/posts/110613301 | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/6345bd89fe134dfd7a0dba40/LTfUYHXCpcwzt3_us0R26.png" alt="Joycaption examples" style="max-height: 500px; width: auto;"> | |
| # I used my Gradio batch caption editor to edit some words and add activation token as ohwx 3d render | |
| # https://www.patreon.com/posts/108992085 | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/6345bd89fe134dfd7a0dba40/BleDJpEMrCMXXRTCPKJqb.png" alt="Gradio batch caption editor" style="max-height: 500px; width: auto;"> | |
| The no caption dataset uses only ohwx 3d render as caption | |
| # I am using my newest 4x_GPU_Rank_1_SLOW_Better_Quality.json on 4X A6000 GPU and train 500 epochs - 114 images | |
| # https://www.patreon.com/posts/110879657</h1> | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/6345bd89fe134dfd7a0dba40/jK75d8i1x5hAHSYSsJNBd.png" alt="Training configuration" style="max-height: 500px; width: auto;"> | |
| ## Inconsistent Dataset Training | |
| This is the first training I made with the below dataset | |
| [Inconsistent-Training-Dataset-Images-Grid.jpg](https://huggingface.co/MonsterMMORPG/3D-Cartoon-Style-FLUX/resolve/main/Inconsistent-Training-Dataset-Images-Grid.jpg) | |
| When you pay attention to the grid image above shared, you will see that the dataset is not consistent | |
| It has total 114 images | |
| This training total step count was 500 * 114 / 4 (4x GPU - batch size 1) = 14250 | |
| It took like 37 hours on 4x RTX A6000 GPU with slow config - faster config would take like half | |
| There were 2 trainings made with this dataset. Epoch 500 checkpoints are named as below | |
| SECourses_Style_Inconsistent_DATASET_NO_Captions.safetensors | |
| SECourses_Style_Inconsistent_DATASET_With_Captions.safetensors | |
| Their checkpoints are saved in below folders | |
| Training-Checkpoints-NO-Captions | |
| Training-Checkpoints-With-Captions | |
| Its grid results are shared below | |
| https://huggingface.co/MonsterMMORPG/3D-Cartoon-Style-FLUX/resolve/main/Inconsistent-Training-Dataset-Results-Grid-26100x23700px.jpg | |
| When you pay attention to above image you will see that it has inconsistent results | |
| 1 : https://youtu.be/bupRePUOA18 | |
| ### [**FLUX: The First Ever Open Source txt2img Model Truly Beats Midjourney & Others - FLUX is Awaited SD3**](https://youtu.be/bupRePUOA18) | |
| [](https://youtu.be/bupRePUOA18) | |
| 2 : https://youtu.be/nySGu12Y05k | |
| ### [**FLUX LoRA Training Simplified: From Zero to Hero with Kohya SS GUI (8GB GPU, Windows) Tutorial Guide**](https://youtu.be/nySGu12Y05k) | |
| [](https://youtu.be/nySGu12Y05k) | |
| 3 : https://youtu.be/-uhL2nW7Ddw | |
| ### [**Blazing Fast & Ultra Cheap FLUX LoRA Training on Massed Compute & RunPod Tutorial - No GPU Required!**](https://youtu.be/-uhL2nW7Ddw) | |
| [](https://youtu.be/-uhL2nW7Ddw) | |
| Hopefully will share trained LoRA on Hugging Face and CivitAI along with full dataset including captions. | |
| I got permission to share dataset but can't be used commercially. | |
| Also I will hopefully share full workflow in the CivitAI and Hugging Face LoRA pages. | |
| So far 450 epochs completed | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/6345bd89fe134dfd7a0dba40/7ZFz_ZW53ipp8LHYuPPSg.png" alt="Training progress" style="max-height: 500px; width: auto;"> |