stable-diffusion-webui-directml
triton
stable-diffusion-webui-directml | triton | |
---|---|---|
74 | 2 | |
1,577 | 72 | |
- | - | |
9.9 | 9.7 | |
6 days ago | 4 days ago | |
Python | C++ | |
GNU Affero General Public License v3.0 | 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-webui-directml
- stable diffusion compliant with amd gpu or not?
-
RuntimeError: Could not allocate tensor with 4915840 bytes. There is not enough GPU video memory available!
I'm getting this error using (https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues), freshly installed. I'm running it on an AMD RX 6700 XT with 12gb of vram. Generating a single image at default settings (512x512, 20 steps, etc.) I can do simple prompts (i.e. "kitty cat") but as soon as I add a couple more tags, I get the aforementioned error message, usually 20-30% into generating an image. I went through this thread (https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/38) and tried every solution I saw, most of them being variations of adding --medvram --precision full --no-half --no-half-vae --opt-split-attention-v1 --opt-sub-quad-attention --disable-nan-check to the commandline arguments. What else might I be able to try? Thanks.
-
Best AMD SD Guide for 2023?
i use automatic 1111 you can find the installation on the github , this branch https://github.com/lshqqytiger/stable-diffusion-webui-directml and it works fine although the speed is what it is, i also have a old GPU.
-
Just how much VRAM do I need? It keeps saying I don't have enough with a 7900xt.
I'm using this one: https://github.com/lshqqytiger/stable-diffusion-webui-directml
-
I am confused regarding same seed = same picture. Any explanations or insights? The journey for this in comments.
- https://github.com/lshqqytiger/stable-diffusion-webui-directm - starting webuser-ui with COMMANDLINE_ARGS=--opt-sub-quad-attention –disable-nan-check - AMD 8GB Radeon Pro WX7100
- ¿Quién fue a la marcha contra la IA en el Obelisco? Cuenten cómo estuvo
-
StableDiffusion will only use my CPU?
I'm running this fork (https://github.com/lshqqytiger/stable-diffusion-webui-directml) on a pc with a Ryzen 5700x and a Radeon RX 6700 XT 12 GB Video Card.
-
(AMD) Random Running Out of Memory Error After Generation
I am using direct-ml fork
-
Stable Diffusion on AMD 6900XT is Super Slow
Im running Stable diffusion on my 6900XT, and I feel like its way slower than normal. Using the updated Webui https://github.com/lshqqytiger/stable-diffusion-webui-directml.
-
Stable Diffusion DirectML on AMD APU only (no external GPU) - Ram Usage?
This refers to the use of iGPUs (example: Ryzen 5 5600G). No graphic card, only an APU. The DirectML Fork of Stable Diffusion (SD in short from now on) works pretty good with AMD. But not only with the GPUs, but also with only-APUs without GPUs.
triton
-
How to use AMD GPU?
cd .. git clone https://github.com/ROCmSoftwarePlatform/triton.git -b release/pytorch_2.0 cd triton/python pip3 install cmake pip3 install -e .
-
Run Stable-Diffusion locally with a AMD GPU (7900XT) on Windows 11
Someone I know returned their 4080 (had a horrible coil whine he said) and yesterday his new 7900XTX came in and he did some testing. Now he can't use xformers and he did not have the sdp optimization on (iow no optimizations) using 5.5.0 beta on docker (that hurts a bit too) he was getting about 16it/s for 512sq and at 768sq he was getting 5.25ish it/s. I had him try with the SDP but optimization but docker is new to him and for some reason I saw no gains, or losses, when it was used (as if docker ignored it). His next test will be for training (which is why he got the card and I will as well). Another thing that hurts is no Triton but here is what he told me yesterday "regarding the 7900 XTX. Inference is fine, around 16 it/s. I couldn't get the training to work, mostly because of what I assume is a bug with the ROCm fork of Triton that's currently in development ( https://github.com/ROCmSoftwarePlatform/triton )."
What are some alternatives?
SHARK - SHARK - High Performance Machine Learning Distribution
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
StableDiffusionUI - Stable Diffusion UI: Diffusers (CUDA/ONNX)
sd-webui-controlnet - WebUI extension for ControlNet
automatic - SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
stable-diffusion-webui - Stable Diffusion web UI
OnnxDiffusersUI - UI for ONNX based diffusers
multidiffusion-upscaler-for-automatic1111 - Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
sd-webui-lobe-theme - 🅰️ Lobe theme - The modern theme for stable diffusion webui, exquisite interface design, highly customizable UI, and efficiency boosting features.
sd-dynamic-prompts - A custom script for AUTOMATIC1111/stable-diffusion-webui to implement a tiny template language for random prompt generation
sd-webui-segment-anything - Segment Anything for Stable Diffusion WebUI
civitai - A repository of models, textual inversions, and more