issue192:tutoriel1
Différences
Ci-dessous, les différences entre deux révisions de la page.
Prochaine révision | Révision précédente | ||
issue192:tutoriel1 [2023/04/29 18:44] – créée auntiee | issue192:tutoriel1 [2023/05/03 14:41] (Version actuelle) – andre_domenech | ||
---|---|---|---|
Ligne 1: | Ligne 1: | ||
- | Given I am still a bit of a newbie myself, I thought I should note some of the problems I have run into with Stable Diffusion (SD.) In order to support the graphics, I upgraded my computer to a gamer desktop with a Nvidia card. The new system (CYBERPOWERPC Gamer Xtreme VR Gaming PC with an Nvidia GeForce RTX 3060, 12GB) was initially only slightly faster than the CPU option. The screen capture below shows the new computer configurations. | + | **Given I am still a bit of a newbie myself, I thought I should note some of the problems I have run into with Stable Diffusion (SD.) In order to support the graphics, I upgraded my computer to a gamer desktop with a Nvidia card. The new system (CYBERPOWERPC Gamer Xtreme VR Gaming PC with an Nvidia GeForce RTX 3060, 12GB) was initially only slightly faster than the CPU option. The screen capture below shows the new computer configurations.** |
- | In order to address the slow imaging speed, I looked at the Settings tab in SD and found that it was set to use the CPU not GPU. (Also note the presence of the Beta Channel version option which may fix some issues and add new options.) | + | Étant donné que je reste un peu débutant moi-même, je pensais que je devais noter certains des problèmes que j’ai rencontrés avec Stable Diffusion (SD). Pour pouvoir prendre en charge les graphismes, j’ai mis à niveau mon ordinateur vers un bureau pour joueur avec une carte Nvidia. Le nouveau système (CYBERPOWERPC Gamer Xtreme VR Gaming PC avec une carte Nvidia GeForce RTX 3060, à 12 Go) était au départ seulement un chouïa plus rapide que l' |
+ | |||
+ | **In order to address the slow imaging speed, I looked at the Settings tab in SD and found that it was set to use the CPU not GPU. (Also note the presence of the Beta Channel version option which may fix some issues and add new options.) | ||
I could not turn off the use CPU option, leading me to realize that Nvidia drivers were not installed by default when installing Ubuntu Studio. Nvidia drivers were then installed using the default, proprietary - tested version. | I could not turn off the use CPU option, leading me to realize that Nvidia drivers were not installed by default when installing Ubuntu Studio. Nvidia drivers were then installed using the default, proprietary - tested version. | ||
- | Eventually another problem arose. While starting SD, I would sometimes see the following line in the terminal and the browser never opened. | + | Eventually another problem arose. While starting SD, I would sometimes see the following line in the terminal and the browser never opened. |
- | qt.qpa.plugin: Could not load the Qt platform plugin " | + | Afin de pouvoir corriger la lenteur de la création d’image, j’ai regardé l’onglet Settings dans SD et j’ai vu qu’il était réglé pour utiliser le CPU et pas le GPU. (Notez aussi la présence d’une option de la version Beta Channel qui corrigera peut-être quelques problèmes et ajoutera de nouvelles options.) |
- | This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem. | + | Je n’arrivais pas à désactiver l’option « use CPU » (utiliser le CPU) et c'est ainsi que je me suis rendu compte que les pilotes Nvidia n’étaient pas installés par défaut lors de l’installation d’Ubuntu Studio. J’ai alors installé les pilotes Nvidia par défaut en utilisant la version propriétaire et testée. Une modification de la configuration des pilotes a donné une amélioration spectaculaire dans la vitesse de création des images : quelques secondes au lieu de plusieurs minutes. |
- | To fix the problem, first close the program (type Ctrl+c {Enter}) and then close the Browser tab. I could fix the above problem each time it happened by pasting the command below in the same terminal window: | + | Finalement, j’ai rencontré un autre problème. En démarrant SD, je voyais parfois la ligne suivante dans le terminal et mon navigateur ne s’est jamais ouvert. |
+ | |||
+ | qt.qpa.plugin: | ||
+ | |||
+ | This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem. (Cette application n'a pas démarré parce qu' | ||
+ | |||
+ | **To fix the problem, first close the program (type Ctrl+c {Enter}) and then close the Browser tab. I could fix the above problem each time it happened by pasting the command below in the same terminal window: | ||
Ligne 20: | Ligne 28: | ||
./start.sh {Enter} | ./start.sh {Enter} | ||
- | Thanks to ljubomirb | + | Thanks to ljubomirb |
- | Afterwards I sometimes ran into the problem again with the CPU selected and the fix was to simply reboot. Looking at the Easy Diffusion Generate panel (current version 2.5.31), changes are often made over several days, see the What’s New tab on the top right on the left side of your web browser interface. | + | Pour corriger le problème, fermez d’abord le programme |
- | As noted in the introductory article, Stable Diffusion part 1, the prompt is the top and likely most important option. It gets saved as part of the image name. Depending on your purpose, you may eventually want to save additional information automatically. To do so, select the Settings tab, next to the Generate tab and with the Auto-Save Images on, select a metadata format such as json or txt. A json file can simply be selected to produce the same file, with txt, information will need to be manually input. Use the full path for the location of your Auto-Saved images. | + | export QT_QPA_PLATFORM=offscreen |
- | You may also use the Download images button for a single image. As I understand it, SD is deterministic, | + | Appuyez sur Entrée et redémarrez Easy Diffusion : |
+ | |||
+ | ./start.sh puis Entrée | ||
+ | |||
+ | Remerciements à ljubomirb (https:// | ||
+ | |||
+ | **Afterwards I sometimes ran into the problem again with the CPU selected and the fix was to simply reboot. Looking at the Easy Diffusion Generate panel (current version 2.5.31), changes are often made over several days, see the What’s New tab on the top right on the left side of your web browser interface. | ||
+ | |||
+ | As noted in the introductory article, Stable Diffusion part 1, the prompt is the top and likely most important option. It gets saved as part of the image name. Depending on your purpose, you may eventually want to save additional information automatically. To do so, select the Settings tab, next to the Generate tab and with the Auto-Save Images on, select a metadata format such as json or txt. A json file can simply be selected to produce the same file, with txt, information will need to be manually input. Use the full path for the location of your Auto-Saved images. ** | ||
+ | |||
+ | Par la suite, j’ai parfois rencontré le problème à nouveau avec le CPU sélectionné et il fallait tout simplement redémarrer. En regardant le panneau Easy Diffusion Generate (la version actuelle est la 2.5.31), des modifications sont souvent faites sur plusieurs jours : regardez l’onglet What’s New en haut à droite côté gauche de l’interface de votre navigateur Web. | ||
+ | |||
+ | Comme noté dans l’article de présentation, | ||
+ | |||
+ | **You may also use the Download images button for a single image. As I understand it, SD is deterministic, | ||
The default image size is 512x512 px and if you choose a smaller size, you are warned that small image sizes (less than the default) can cause bad image quality. If only one dimension is smaller than 512 you may not get the warning but the image quality is likely nevertheless of bad quality. Larger image sizes can also have an undesirable effect on the generated image. While trying to generate an image of a baby with wide open eyes with the size set to 1024x1024 px, multiple faces were always created. Reducing the size to the default 512x512 px produced the desired results. You can then move the cursor over the image in question and select the upscale option that pops-up. | The default image size is 512x512 px and if you choose a smaller size, you are warned that small image sizes (less than the default) can cause bad image quality. If only one dimension is smaller than 512 you may not get the warning but the image quality is likely nevertheless of bad quality. Larger image sizes can also have an undesirable effect on the generated image. While trying to generate an image of a baby with wide open eyes with the size set to 1024x1024 px, multiple faces were always created. Reducing the size to the default 512x512 px produced the desired results. You can then move the cursor over the image in question and select the upscale option that pops-up. | ||
- | When making your first images you will likely be impressed but eventually you will recognize various issues. For example using the prompt “two small possums, photo realistic, | + | When making your first images you will likely be impressed but eventually you will recognize various issues. For example using the prompt “two small possums, photo realistic, |
+ | |||
+ | Vous pouvez également utiliser le bouton Download images pour une seule image. Tel que je le comprends, SD est déterministe et, normalement, | ||
+ | |||
+ | La taille d’une image par défaut est de 512 x 512 px et, si vous choisissez une plus petite taille, un avertissement s’affichera vous indiquant qu'une petite taille d’image (moins que la taille par défaut) peut engendrer une mauvaise qualité de l’image. Si une seule dimension est plus petite que 512, l’avertissement ne s’affichera peut-être pas, mais la qualité de l’image sera néanmoins tout de même mauvaise. Des tailles d’image plus grandes peuvent aussi affecter l’image générée de façon indésirée. Quand j’essayais de générer l’image d’un bébé avec les yeux grand ouverts, la taille de l' | ||
+ | |||
+ | Quand vous créerez vous premières images, vous serez sans doute très impressionné, | ||
+ | |||
+ | **Similarly it can’t do a Pablo Picasso rendering of yourself because your photographs were also not part of the training. That said, try inputting your name in the prompt and see what you get. I thought I would end with a more desirable image, create something like the below with the prompt library with fireplace burning with a single bay window. No fire is in the fireplace in the below image possibly because the prompt was worded incorrectly but it may be because of the viewing angle. You might want to bump up the number of images to 10 in the options below the prompt to make ten different versions. You may want to hold off on using that parameter if you don’t have a more capable graphic card otherwise the wait time may be significant. | ||
- | Similarly it can’t do a Pablo Picasso | + | De la même façon, il ne peut pas faire une image de vous-même à la Pablo Picasso |
issue192/tutoriel1.1682786681.txt.gz · Dernière modification : 2023/04/29 18:44 de auntiee