Datei:Demonstration of inpainting and outpainting using Stable Diffusion (step 4 of 4).png
Personen-Konto
Diese Datei stammt aus Wikimedia Commons und kann von anderen Projekten verwendet werden. Die Beschreibung von deren Dateibeschreibungsseite wird unten angezeigt.
Beschreibung
| BeschreibungDemonstration of inpainting and outpainting using Stable Diffusion (step 4 of 4).png |
Demonstration of the usage of inpainting and outpainting techniques on algorithmically-generated artworks created using the Stable Diffusion V1-4 AI diffusion model. Not only is Stable Diffusion capable of generating new images from scratch via text prompt, it is also capable of providing guided image synthesis for enhancing existing images, through the use of the model's diffusion-denoising mechanism. This image aims to illustrate the process in which Stable Diffusion can be used to perform both inpainting and outpainting, as one part out of four images showing each step of the procedure.
All artworks created using a single NVIDIA RTX 3090. Front-end used for the entire generation process is Stable Diffusion web UI created by AUTOMATIC1111.
An initial 512x768 image was algorithmically-generated with Stable Diffusion via txt2img using the following prompts:
Then, two passes of the SD upscale script using "Real-ESRGAN 4x plus anime 6B" were run within img2img. The first pass used a tile overlap of 64, denoising strength of 0.3, 50 sampling steps with Euler a, and a CFG scale of 7. The second pass used a tile overlap of 128, denoising strength of 0.1, 10 sampling steps with Euler a, and a CFG scale of 7. This creates our initial 2048x3072 image to begin working with. Unfortunately for her (and fortunately for the purpose of this demonstration), it appears that the AI neglected to give this woman one of her arms.
Using the "Outpainting mk2" script within img2img, the bottom of the image was extended by 512 pixels (via two passes, each pass extending 256 pixels), using 100 sampling steps with Euler a, denoising strength of 0.8, CFG scale of 7.5, mask blur of 4, fall-off exponent value of 1.8, colour variation set to 0.03. The prompts used were identical to those utilised during the first step. This subsequently increases the image's dimensions to 2048x3584, while also revealing the woman's midriff, belly button and skirt, which were previously absent from the original AI-generated image.
In GIMP, I drew a very shoddy attempt at a human arm using the standard paintbrush. This will provide a guide for the AI model to generate a new arm.
Using the inpaint feature for img2img, I drew a mask over the arm drawn in the previous step, along with a portion of the shoulder. The following settings were used for all passes:
An initial pass was run using the following prompts:
This created the arm; another subsequent pass was then done to fine-tune deformations and blemishes around the newly generated arm along the sleeve. Drawing a new mask over the shoulder, the following prompt was used:
The outcome of this pass resulted in the final image. |
| Datum | |
| Quelle | Eigenes Werk |
| Urheber | Benlisquare |
| Genehmigung (Weiternutzung dieser Datei) |
As the creator of the output images, I release this image under the licence displayed within the template below.
The Stable Diffusion AI model is released under the CreativeML OpenRAIL-M License, which "does not impose any restrictions on reuse, distribution, commercialization, adaptation" as long as the model is not being intentionally used to cause harm to individuals, for instance, to deliberately mislead or deceive, and the authors of the AI models claim no rights over any image outputs generated, as stipulated by the license.
|
Lizenz
- Dieses Werk darf von dir
- verbreitet werden – vervielfältigt, verbreitet und öffentlich zugänglich gemacht werden
- neu zusammengestellt werden – abgewandelt und bearbeitet werden
- Zu den folgenden Bedingungen:
- Namensnennung – Du musst angemessene Urheber- und Rechteangaben machen, einen Link zur Lizenz beifügen und angeben, ob Änderungen vorgenommen wurden. Diese Angaben dürfen in jeder angemessenen Art und Weise gemacht werden, allerdings nicht so, dass der Eindruck entsteht, der Lizenzgeber unterstütze gerade dich oder deine Nutzung besonders.
- Weitergabe unter gleichen Bedingungen – Wenn du das Material wiedermischst, transformierst oder darauf aufbaust, musst du deine Beiträge unter der gleichen oder einer kompatiblen Lizenz wie das Original verbreiten.
| Es ist erlaubt, die Datei unter den Bedingungen der GNU-Lizenz für freie Dokumentation, Version 1.2 oder einer späteren Version, veröffentlicht von der Free Software Foundation, zu kopieren, zu verbreiten und/oder zu modifizieren; es gibt keine unveränderlichen Abschnitte, keinen vorderen und keinen hinteren Umschlagtext.
Der vollständige Text der Lizenz ist im Kapitel GNU-Lizenz für freie Dokumentation verfügbar.http://www.gnu.org/copyleft/fdl.htmlGFDLGNU Free Documentation Licensetruetrue |
Kurzbeschreibungen
In dieser Datei abgebildete Objekte
Motiv
Einige Werte ohne einen Wikidata-Eintrag
27. September 2022
image/png
4.665.181 Byte
3.584 Pixel
2.048 Pixel
6984d404830386b8a1f1242f8fe483589ceb263b
Dateiversionen
Klicke auf einen Zeitpunkt, um diese Version zu laden.
| Version vom | Vorschaubild | Maße | Benutzer | Kommentar | |
|---|---|---|---|---|---|
| aktuell | 22:00, 28. Sep. 2022 | 2.048 × 3.584 (4,45 MB) | wikimediacommons>Benlisquare | I didn't like how dark the arm turned out, so I re-did it again. Redrew the makeshift arm in a lighter shade in GIMP, then ran two passes of inpainting: Steps: 80, Sampler: Euler a, CFG scale: 17, Seed: 525737653, Denoising strength: 0.6 to generate arm; Steps: 80, Sampler: Euler a, CFG scale: 7, Seed: 653575127, Denoising strength: 0.4 for cleanup. |
Dateiverwendung
Die folgende Seite verwendet diese Datei:



