SOTA Image Captioning Scripts For Stable Diffusion: CogVLM, LLaVA, BLIP-2, Clip-Interrogator (115 Clip Vision Models + 5 Caption Models)
Patreon exclusive posts index to find our scripts easily, <...
2024-10-02 11:00:00 +0000 UTC View Post
Patreon exclusive posts index to find our scripts easily, <...
2024-10-02 11:00:00 +0000 UTC View Post
MimicPC is a cloud service that lets you use AI applications seamlessly in your browser while everything runs on remote cloud servers, providing permanent sto...
2024-09-25 09:19:31 +0000 UTC View Post
You can download our APP from here : https://www.patr...
2024-09-22 22:51:54 +0000 UTC View Post
Patreon exclusive posts index to find our scripts easily, <...
2024-09-21 15:31:55 +0000 UTC View Post
Patreon exclusive posts index to find our scripts easily, <...
2024-09-20 00:49:09 +0000 UTC View Post
Full Fine Tuning / DreamBooth of FLUX yields way better results than LoRA training as expected, overfitting and bleeding reduced a lot, check oldest comment for more information, images LoRA vs Fin...
2024-09-16 10:47:40 +0000 UTC View Post
Medium article : 2024-09-14 22:37:09 +0000 UTC View Post
Patreon exclusive posts index to find our scripts easily, <...
2024-09-13 15:33:00 +0000 UTC View Post
Started training my 256 images on FLUX with 8x GPU - Dataset is not ready yet, not very good sharpness and lightning but so many people asking expressions so i am taking a break from research :) - ...
2024-09-10 21:54:14 +0000 UTC View PostNOW WE HAVE A MUCH BETTER NEW APP PLEASE USE IT
https://www.patreon.com/posts/1121...
2024-09-10 20:00:00 +0000 UTC View PostPatreon exclusive posts index to find our scripts easily, <...
2024-09-10 16:49:36 +0000 UTC View Post
I have done total 104 different LoRA trainings and compared each one of them to find the very best hyper parameters and the workflow for FLUX LoRA training by using Kohya GUI training script.
I have been using a machine on RunPod that has 8x RTX A6000 over a week now. I have done all the following experiments with each one being 3000 steps.
Latest configs shared on : 2024-09-09 21:00:00 +0000 UTC View Post
CivitAI Link : https://civitai.com/models/731347
Hugging Face Link : ...
2024-09-08 00:11:27 +0000 UTC View Post
Rope NEXT Update Has Arrived - both Rope Live and Rope Alucard Versions Are Updated
Both works with CUDA 11.8 and also CUDA 12.4
Both works on Massed Compute p...
2024-09-07 01:32:06 +0000 UTC View Post
The installer zip files are provided in this post : https://www.patreon.com/posts/103765029
It...
2024-09-07 00:41:01 +0000 UTC View Post
Raw FLUX LoRA Output vs SwarmUI Quick 2x Upscale Button vs Our SUPIR APP Upscale (Face Upscale ON) : https://imgsli.com/MjkzODAz/...
2024-09-03 22:16:06 +0000 UTC View Post
I started training a public LoRA style (2 seperate training each on 4x A6000).
Experimenting captions vs non-captions. So we will see which yields best results for style training on FLUX.
... 2024-09-02 23:48:09 +0000 UTC View Post
I will update this page as I progress. I am just starting so I will add the info. Nothing ready yet
FOLLOW THIS THREAD NOW FOR TUTORIAL : 2024-08-30 10:00:00 +0000 UTC View Post
Multi-GPU batch caption with JoyCaption. JoyCaption uses Meta-Llama-3.1–8B and google/siglip-so400m-patch14–384 and a fine tuned image captioning neural network.
Here a Hugging Face space that you can test it yourself : https://huggingface.co/s...
2024-08-24 02:13:07 +0000 UTC View Post
ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS 2023, Spotlight)
Official Repo : 2024-08-19 01:37:52 +0000 UTC View Post
Patreon exclusive posts index to find our scripts easily, <...
2024-08-18 21:57:40 +0000 UTC View Post
Scripts are shared here : https://www.patreon.com/posts/forge-web-ui-and-110323512
Uses offici...
2024-08-18 12:42:21 +0000 UTC View Post
Patreon exclusive posts index to find our scripts easily, 2024-08-16 22:00:00 +0000 UTC View Post
I just updated the automatic FLUX models downloader scripts with newest models and features. Therefore I decided to test all models comprehensively with respected to their peak VRAM usage and also ...
2024-08-15 03:25:49 +0000 UTC View PostI have been recently contacted by the original SUPIR developers that they published SUPIR online with better features and they are generated funds from this service to develop SUPIR v2 and SUPIR vi...
2024-08-15 00:39:17 +0000 UTC View Post
Patreon exclusive posts index to find our scripts easily, <...
2024-08-14 21:11:00 +0000 UTC View Post
AuraSR is a 600M parameter upsampler model derived from the GigaGAN paper. It works super fast and uses a very limited VRAM below 5 GB. It is deterministic upscaler. It works perfect in some images...
2024-08-14 21:10:02 +0000 UTC View Post