multidiffusion-upscaler-for-automatic1111
sd-dynamic-thresholding
multidiffusion-upscaler-for-automatic1111 | sd-dynamic-thresholding | |
---|---|---|
83 | 26 | |
4,459 | 1,019 | |
- | 4.1% | |
7.8 | 7.2 | |
about 1 month ago | 16 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | 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.
multidiffusion-upscaler-for-automatic1111
- Stable Diffusion can't stop generating extra torsos, even with negative prompt. Any suggestions?
-
Reduce Or Remove The Use Of RAM In Image Generation
Use tiled VAE, it will save VRAM: pkuliyi2015/multidiffusion-upscaler-for-automatic1111: Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0 (github.com)
-
How I do I fix these boxes/lines appearing while using Ultimate SD upscale + CN tiles? All the details are in my comment below. Please Helps. MANY THANKS !!!
My favorite solution is to not use ultimate Sd upscale and instead use multidiffusion-upscaler.
- Is there any way to purge the VRAM of your card after getting OOT'ed other than restarting the Web UI?
-
Not able to generate more than 400*400 image
sure, i personally use 'tiled diffusion' https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111, works like charm also use adetailer for faces if its needed.
-
GTX 1070 slow render speeds
What worked for my 1080 was using TiledVAE and turning down the quality of my previews - I don't pay much attention to it/s but it's definitely faster than using --medvram, and now I can handle batches and large resolutions without things exploding on me.
-
Initial release of A8R8 (Alternate Reality), an opinionated interface for Stable Diffusion image generation, works with A1111. Docker installation included. Open source and runs locally!
I would highly recommend adding https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 to your A1111 installation, TiledVAE is enabled automatically under the hood in A8R8; this will allow you to get even larger generations before getting an out of memory error. You'll get a Tiled Diffusion checkbox with some reasonable hardcoded defaults as well.
- I love the Tile ControlNet, but it's really easy to overdo. Look at this monstrosity of tiny detail I made by accident.
-
Can you generate 2048x2048 images with an 8GB GPU?
Use Tiled VAE https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111
-
SDXL 0.9 vs SD 2.1 vs SD 1.5 (All base models) - Batman taking a selfie in a jungle, 4k
That's weird. 10GB should allow you to hires to 2048x2048 at least. Use Tiled VAE extension https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 that will allow you to go even beyond that.
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?
ultimate-upscale-for-automatic1111
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.
automatic - SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
Stable-Diffusion - Stable Diffusion, SDXL, LoRA Training, DreamBooth Training, Automatic1111 Web UI, DeepFake, Deep Fakes, TTS, Animation, Text To Video, Tutorials, Guides, Lectures, Courses, ComfyUI, Google Colab, RunPod, NoteBooks, ControlNet, TTS, Voice Cloning, AI, AI News, ML, ML News, News, Tech, Tech News, Kohya LoRA, Kandinsky 2, DeepFloyd IF, Midjourney
ComfyUI_TiledKSampler - Tiled samplers for ComfyUI
adetailer - Auto detecting, masking and inpainting with detection model.
Waifu2x-Extension-GUI - Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, Real-CUGAN, RTX Video Super Resolution VSR, SRMD, RealSR, Anime4K, RIFE, IFRNet, CAIN, DAIN, and ACNet.
sd_webui_SAG
mixture-of-diffusers - Mixture of Diffusers for scene composition and high resolution image generation
sd-dynamic-prompts - A custom script for AUTOMATIC1111/stable-diffusion-webui to implement a tiny template language for random prompt generation
stable-diffusion-webui-two-shot - Latent Couple extension (two shot diffusion port)