Stable-Diffusion
sd-dynamic-thresholding
Stable-Diffusion | sd-dynamic-thresholding | |
---|---|---|
30 | 26 | |
1,760 | 1,019 | |
- | 4.8% | |
9.8 | 7.2 | |
6 days ago | 22 days ago | |
Jupyter Notebook | Python | |
GNU General Public License v3.0 only | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stable-Diffusion
- Scalable Load Balancing Having Cloud GPU Service Salad Tutorial With Whisper Transcriber Gradio APP
- FLaNK AI-April 22, 2024
-
OneTrainer Fine Tuning vs Kohya SS DreamBooth & Huge Research of OneTrainer’s Masked Training
So stay subscribed and open notification bells to not miss : https://www.youtube.com/SECourses
-
Finding Best Training Hyper Parameters / Configuration Is Neither Cheap Nor Easy
You can use A6000 GPU on MassedCompute with our template for only 31 cents per hour. Follow instructions here (still WIP) : https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Tutorials/OneTrainer-Master-SD-1_5-SDXL-Windows-Cloud-Tutorial.md
-
Compared Effect Of Image Captioning For SDXL Fine-tuning / DreamBooth Training for a Single Person, 10.3 GB VRAM via OneTrainer
The tutorial will be on our channel : https://www.youtube.com/SECourses
-
A New Gold Tutorial For RunPod & Linux Users : How To Use Storage Network Volume In RunPod & Latest Version Of Automatic1111
Patreon exclusive posts index
- SUPIR Full Tutorial + 1 Click 12GB VRAM Windows & RunPod / Linux Installer + Batch Upscale + Comparison With Magnific
-
Beware When Buying M2 NVMe SSDs: Netac NV7000, Kioxia Exceria Plus G2, Kingston and Sandisk Compared
Used Writing Speed & Cache Testing Python Script ⤵️ https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/CustomPythonScripts/gen_file.py
- Viral Paper Tested MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
-
56 Stable Diffusion And Related Generative AI Tutorials Organized List
Our 1,200+ Stars GitHub Stable Diffusion and other tutorials repo ⤵️ https://github.com/FurkanGozukara/Stable-Diffusion
sd-dynamic-thresholding
-
ZeroDiffusion -- a clean zero terminal SNR training 1.5 base model + experimental inpainting model
For outputs to look right, you will need some form of CFG rescale or dynamic thresholding in order to correct for overexposure (A1111 extensions are linked -- I am told that ComfyUI has nodes available for these functions). A good starting point for CFG rescale is 0.7, as recommended in the paper. I strongly suspect that CFG rescale is not an ideal solution and leaves a substantial training-inference gap, and when using zero terminal SNR models I find that Dynamic Thresholding can give better outputs that are closer to what I expect from the data without the brownout often caused by CFG rescale. A potential starting point for Dynamic Thresholding would be: Restart sampler, 15 CFG scale, Mimic CFG scale 15 7.5, Sawtooth on both scale schedulers, 6 for both minimum values, scheduler value 4, do not separate feature channels, ZERO, STD. You will likely have to experiment a lot with Dynamic Thresholding. (edit: small correction to DT settings)
-
Dynamic Thresholding for comfyui?
Recently switched from A1111 and i love it so far, flexibility to orchestrate complex workflows automatically instead of manual operations is a life changer. Anyhow, one extension i like on A1111 was this one: https://github.com/mcmonkeyprojects/sd-dynamic-thresholding
-
How do I implement Dynamic Thresholding (CFG scale fix) in ComfyUI?
In the Automatic1111 webui, there is a Dynamic Thresholding (CFG scale fix) extension that:
-
How to diffuse better faces?
Ive found using ADetailer (https://github.com/Bing-su/adetailer, using their reccomended advanced settings and face_yolov8n.pt) and Dynamic Thresholding (CFG set to 12 and Mimic to 7) has vastly improved my face renders. (https://github.com/mcmonkeyprojects/sd-dynamic-thresholding) GL!
-
Kohya UI settings as asked (style+character training)
The output LoRA works best with CFG at 4, because at 7 it gets that gasoline colors and contrast of overbaking, but I guess this is a tradeoff of that many steps in total (5200) since the earlier snapshots were not that good in style and with character details. You can use a workaround like the Dynamic Trescholding extention: https://github.com/mcmonkeyprojects/sd-dynamic-thresholding.git - helps a lot in many cases when you want a high CFG but the model/lora overbakes them (it mimics a lower CFG while keeping the high CFG details and prompt alignment).
-
Does anyone know how to create this type of hyper realistic pic?
Use sd-dynamic-thresholding extension (set CFG scale to 12 or more and mimic CFG scale to 7): https://github.com/mcmonkeyprojects/sd-dynamic-thresholding
- ControlNet Reference-Only problems
-
What's your favorite small tweaks to make? I'll go first
Tweak this up or down for small changes. Too far and you’ll get a different image. Extensions like Dynamic Thresholding can let you go much higher without the overexposed look.
-
Blurred/Low quality/Low details images
Turn CFG scale down or maybe use this extension, I've never used Dynamic Thresholding before but I think its what you want
- Dynamic threshold & Offset noise - The answer to oversaturated images?
What are some alternatives?
Fooocus - Focus on prompting and generating
stable-diffusion-webui-anti-burn - Extension for AUTOMATIC1111/stable-diffusion-webui for smoothing generated images by skipping a few very last steps and averaging together some images before them.
multidiffusion-upscaler-for-automatic1111 - Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
adetailer - Auto detecting, masking and inpainting with detection model.
SUPIR - SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild
caption-upsampling - This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.
sd_webui_SAG
CushyStudio - 🛋 The AI and Generative Art platform for everyone
sd-dynamic-prompts - A custom script for AUTOMATIC1111/stable-diffusion-webui to implement a tiny template language for random prompt generation
audiocraft - Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
ultimate-upscale-for-automatic1111