multidiffusion-upscaler-for-automatic1111
mixture-of-diffusers
multidiffusion-upscaler-for-automatic1111 | mixture-of-diffusers | |
---|---|---|
83 | 6 | |
4,459 | 382 | |
- | - | |
7.8 | 4.4 | |
about 1 month ago | 12 months 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.
mixture-of-diffusers
-
ControlNet Tile can generate details for each person in the crowd
Lol. But I know what I started with! I may have linked this above but do check out the mixture of diffusers repo, the image at the top of the readme is what I first tried to reproduce. Here is the prompt from that page:
- Allure of the lake - Txt2Img & region prompter
-
Messing with the denoising loop can allow you to reach new places in latent space. Over 8+ different research papers/Auto1111 extension ideas in a single pipe. Load once and do lots of different things (SD 2.1 or 1.5)
So I've continued to experiment with how many papers I can fit into a single pipe and have them play nicely together. The images below were created by combining the panorama code from omerbt/MultiDiffusion with the ideas from albarji/mixture-of-diffusers. Also turns out nateraw/stable-diffusion-videos can be seen as a special case of a panorama (in latent space rather than prompt space).
-
[R] [N] "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" enables controllable image generation without any further training or finetuning of diffusion models.
No I'm talking about https://github.com/albarji/mixture-of-diffusers but probably not like the spatial controls of MultiDiffusion.
-
You to can create Panorama images 512x10240+ (not a typo) using less then 6GB VRAM (Vertorama works too). A modification of the MultiDiffusion code to pass the image through the VAE in slices then reassemble. Potato computers of the world rejoice.
can you combine this with mixture of diffusers somehow?
-
First version of Stable Diffusion was released on August 22, 2022
If we combine Mixture of Diffusers + MultiDiffusion+ Composer+ cross-domain-compositing and probably some more I'm not thinking of.
What are some alternatives?
ultimate-upscale-for-automatic1111
sd-webui-regional-prompter - set prompt to divided region
automatic - SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
MultiDiffusion - Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)
ComfyUI_TiledKSampler - Tiled samplers for ComfyUI
stable-diffusion-videos - Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
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.
composer - Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"
stable-diffusion-webui-two-shot - Latent Couple extension (two shot diffusion port)
sd-dynamic-thresholding - Dynamic Thresholding (CFG Scale Fix) for Stable Diffusion (StableSwarmUI, ComfyUI, and Auto WebUI)
stable-diffusion-webui-vae-tile-infer - Yet another vae tiling inferer, extension script for AUTOMATIC1111/stable-diffusion-webui.
Stable-Diffusion-Desktop-Client - Stable Diffusion Desktop client for Windows, macOS, and Linux built in Embarcadero Delphi.