NathMath commited on
Commit
4e5cc5a
·
1 Parent(s): 45b629a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -25,9 +25,9 @@ tags:
25
  - Here is a full tutorial to use stable-diffusion-xl-0.9 FROM ZERO!
26
 
27
 
28
- - 1. - Go to Github and find the latest version of ComfyUI, which is a cutting-edge GUI platform for you to use all kinds of diffusion models.
29
- - Note that in the link below, it provides both a standalone version (do not need an extra python environment), and a source version.
30
- - We recommend the first approach because we are all lazy buddies.
31
  - Link: https://github.com/comfyanonymous/ComfyUI
32
  ![step1.png](https://cdn-uploads.huggingface.co/production/uploads/637a0b3f3f8f451d6bd1fd6d/FtaIbRvUivh375NLb9i6L.png)
33
 
@@ -37,22 +37,22 @@ tags:
37
  ![sdxl-step2.png](https://cdn-uploads.huggingface.co/production/uploads/637a0b3f3f8f451d6bd1fd6d/VWJ-h5a2UeHostFfi6d-8.png)
38
 
39
 
40
- - 3. - Get into the folder or the environment you have just created, when you have finished the last step.
41
  - Next, what you can find includes those two ".bat" files named "run_cpu.bat" and "run_nvidia_gpu.bat" respectively.
42
- - Then, choose the suitable version and click it, which means, to use CUDA or not, and double click to run the script.
43
- - Note that with the application of xformers, you do not need to load all of your models simultaneously, but it is going to be stored in RAM and move back and force when interfereing.
44
  ![sdxl-step3.png](https://cdn-uploads.huggingface.co/production/uploads/637a0b3f3f8f451d6bd1fd6d/oXns3ynzBJve2jRJyqN2D.png)
45
 
46
 
47
  - 4. - Download the latest version of stable-diffusion-xl-base-0.9 and stable-diffusion-xl-refiner-0.9 from the official repo on huggingaface.
48
- - It is appreciated that your availability of the model has become unprecedentedly effortless now, so hurry up to try and get on.
49
- - Note that for generation use, you do not need to download all model components, but only the two "safetensors" fron the repo, which are respectively "sd_xl_base_0.9.safetensors" and "sd_xl_refiner_0.9.safetensors".
50
  - Link: https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9
51
  - Link: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-0.9
52
 
53
 
54
  - 5. - Move your "base" and "refiner" models into the ComfyUI's subfolder, like "...\ComfyUI\models\checkpoints\", where "..." means your root folder of your ComfyUI environment.
55
- - Click into the file folder of THIS REPO, and find some files named "sdxl-0.9-...-.json", which is a demo environment I have created for testing and using the stable-diffusion-xl-0.9 in ComfyUI.
56
  - Note that the 3-digit number in the file name represents the version of my demo, and always, you should download the latest one owning the biggest number.
57
  - Link: https://huggingface.co/NathMath/sdxl-0.9-usage/tree/main
58
  ![sdxl-step50.png](https://cdn-uploads.huggingface.co/production/uploads/637a0b3f3f8f451d6bd1fd6d/H_R7z1iTQ2U7DuVgpHuLr.png)
@@ -90,4 +90,4 @@ tags:
90
  ### Q&A
91
 
92
 
93
- - Please feel free to leave all of your questions in the community of this repo, and I will soon answer them if I am able to solve.
 
25
  - Here is a full tutorial to use stable-diffusion-xl-0.9 FROM ZERO!
26
 
27
 
28
+ - 1. - Go to Github and find the latest version of ComfyUI, which is a cutting-edge GUI interface for you to flexibly use all kinds of diffusion models.
29
+ - Note that in the link below, it provides both a standalone zip (includes a prepared python environment), and a source version.
30
+ - We highly recommend the first approach because we are all lazy buddies.
31
  - Link: https://github.com/comfyanonymous/ComfyUI
32
  ![step1.png](https://cdn-uploads.huggingface.co/production/uploads/637a0b3f3f8f451d6bd1fd6d/FtaIbRvUivh375NLb9i6L.png)
33
 
 
37
  ![sdxl-step2.png](https://cdn-uploads.huggingface.co/production/uploads/637a0b3f3f8f451d6bd1fd6d/VWJ-h5a2UeHostFfi6d-8.png)
38
 
39
 
40
+ - 3. - Get into the folder or the environment you have just created when you have finished the last step.
41
  - Next, what you can find includes those two ".bat" files named "run_cpu.bat" and "run_nvidia_gpu.bat" respectively.
42
+ - Then, choose the suitable option and click it, which means, to use CUDA (if you have NVDIA GPUs) or not, and double click to run the script.
43
+ - Note that with the application of xformers, you do not need to load all of your models simultaneously, but those gargantuan weights are going to be temporarily stored in RAM and move back and force when interfereing.
44
  ![sdxl-step3.png](https://cdn-uploads.huggingface.co/production/uploads/637a0b3f3f8f451d6bd1fd6d/oXns3ynzBJve2jRJyqN2D.png)
45
 
46
 
47
  - 4. - Download the latest version of stable-diffusion-xl-base-0.9 and stable-diffusion-xl-refiner-0.9 from the official repo on huggingaface.
48
+ - It is appreciated that your availability of the model has become unprecedentedly effortless now, so hurry up and get on.
49
+ - Note that for generation use, you do not need to download all model components, but only the two "safetensors" from the repo, which are respectively "sd_xl_base_0.9.safetensors" and "sd_xl_refiner_0.9.safetensors".
50
  - Link: https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9
51
  - Link: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-0.9
52
 
53
 
54
  - 5. - Move your "base" and "refiner" models into the ComfyUI's subfolder, like "...\ComfyUI\models\checkpoints\", where "..." means your root folder of your ComfyUI environment.
55
+ - Click the file folder of THIS REPO and find some files named "sdxl-0.9-...-.json", which is a demo environment I have created for testing and using the stable-diffusion-xl-0.9 in ComfyUI.
56
  - Note that the 3-digit number in the file name represents the version of my demo, and always, you should download the latest one owning the biggest number.
57
  - Link: https://huggingface.co/NathMath/sdxl-0.9-usage/tree/main
58
  ![sdxl-step50.png](https://cdn-uploads.huggingface.co/production/uploads/637a0b3f3f8f451d6bd1fd6d/H_R7z1iTQ2U7DuVgpHuLr.png)
 
90
  ### Q&A
91
 
92
 
93
+ - Please feel free to leave any questions in the community of this repo, and I will soon answer them if I am able to solve.