Archivo:Demonstration of DreamBooth AI model fine-tuning for Stable Diffusion using Jimmy Wales training data from Wikimedia Commons.png

Contenido de la página no disponible en otros idiomas.
De Wikipedia, la enciclopedia libre

Ver la imagen en su resolución original(2304 × 2048 píxeles; tamaño de archivo: 5,14 MB; tipo MIME: image/png)

Resumen

Descripción

Demonstration of the use of DreamBooth to fine-tune a text-to-image diffusion model (in this particular case, Stable Diffusion) so that it can algorithmically generate highly specialised and customised image outputs. This demonstration features six output images of Jimmy Wales, founder of Wikipedia, performing bench press exercises at a fitness gym.

Procedure/Methodology

The model checkpoint was fine-tuned in DreamBooth using 38 different free-licence images of Jimmy Wales obtained from Category:Jimmy Wales on Wikimedia Commons, using Stable Diffusion V1-5 as the base model checkpoint to be trained. Specifically, the following images were used as training data:

Using d8ahazard's DreamBooth_V2 fork of Stable Diffusion web UI created by AUTOMATIC1111, a new model based on Stable Diffusion V1-5 (sd-v1-5-pruned-emaonly.ckpt) was created with "pndm" selected as the scheduler, and the following options were chosen:

  • Initialisation text: photo of jimmywalesstare man
  • Classification text: photo of a man
  • Learning rate: 0.000005
  • Total number of classification images to use: 50
  • Training steps: 4000
  • Batch size: 1
  • Class batch size: 1
  • Seed: -1
  • Resolution: 512
  • Save a checkpoint every N steps: 500

The model was then subsequently trained using the 38 images listed earlier. The DreamBooth training process, along with the image generation process outlined later below, was performed using an NVIDIA RTX 4090; since Ada Lovelace chipsets (using compute capability 8.9, which requires CUDA 11.8) are not fully supported by the pyTorch dependency libraries currently used by Stable Diffusion, I've used a custom build of xformers, along with pyTorch cu116 and cuDNN v8.6, as a temporary workaround.

After completion of the training of the new model, a batch of 768x1024 images were generated with txt2img in Stable Diffusion, using the model checkpoint taken at 1000 training steps, and with the following prompts:

Prompt: photo of jimmywalesstare man at the (gym) performing (bench press), muscular body, athletic body, Nikon D7500, 4K, sharp focus, photorealistic high-quality, volumetric lighting, close-up, detailed face

Negative prompt: (((multiple people))), (((out of frame))), (((no face))), ((deformed hands)), extra limbs, ((ugly)), (((deformed))), ((bad anatomy)), ((mangled)), (((censored))), (blurry), (((distorted face))), mutation, amputee, hugging, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, broken body, mutated, extra hands, extra feet, extra arms, extra legs, multiple views, lowres

Settings: Steps: 100, Sampler: DPM2 a, CFG scale: 12, Size: 768x1024, Highres. fix, Upscale latent space off, Denoising strength: 0.7

The final images were taken from this generated batch.
Fecha
Fuente Trabajo propio
Autor Benlisquare
Permiso
(Reutilización de este archivo)
Output images

As the creator of the output images, I release this image under the licence displayed within the template below.

Stable Diffusion AI model

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.

DreamBooth

The Stable Diffusion implementation of DreamBooth by XavierXiao, of which d8ahazard's DreamBooth_V2 fork of the Stable Diffusion web UI is based on, is licenced under the MIT License.

Training data used to create the customised model checkpoint
All 38 images used to train the model via DreamBooth were free-licence images obtained from Wikimedia Commons. For detailed licencing information, refer to the file descriptions of each individual image.

Licencia

Yo, titular de los derechos de autor de esta obra, la publico en los términos de las siguientes licencias:
w:es:Creative Commons
atribución compartir igual
Este archivo está disponible bajo la licencia Creative Commons Attribution-Share Alike 4.0 International.
Eres libre:
  • de compartir – de copiar, distribuir y transmitir el trabajo
  • de remezclar – de adaptar el trabajo
Bajo las siguientes condiciones:
  • atribución – Debes otorgar el crédito correspondiente, proporcionar un enlace a la licencia e indicar si realizaste algún cambio. Puedes hacerlo de cualquier manera razonable pero no de manera que sugiera que el licenciante te respalda a ti o al uso que hagas del trabajo.
  • compartir igual – En caso de mezclar, transformar o modificar este trabajo, deberás distribuir el trabajo resultante bajo la misma licencia o una compatible como el original.
GNU head Se autoriza la copia, distribución y modificación de este documento bajo los términos de la licencia de documentación libre GNU, versión 1.2 o cualquier otra que posteriormente publique la Fundación para el Software Libre; sin secciones invariables, textos de portada, ni textos de contraportada. Se incluye una copia de la dicha licencia en la sección titulada Licencia de Documentación Libre GNU.
Puedes usar la licencia que prefieras.

Leyendas

Añade una explicación corta acerca de lo que representa este archivo

Elementos representados en este archivo

representa a

Historial del archivo

Haz clic sobre una fecha y hora para ver el archivo tal como apareció en ese momento.

Fecha y horaMiniaturaDimensionesUsuarioComentario
actual10:35 8 ago 2023Miniatura de la versión del 10:35 8 ago 20232304 × 2048 (5,14 MB)Obscure2020Optimized with OxiPNG and ZopfliPNG.
18:47 4 nov 2022Miniatura de la versión del 18:47 4 nov 20222304 × 2048 (6,04 MB)Benlisquare{{Information |Description=Demonstration of the use of DreamBooth to fine-tune a text-to-image diffusion model (in this particular case, Stable Diffusion) so that it can algorithmically generate highly specialised and customised image outputs. This demonstration features six output images of Jimmy Wales, founder of Wikipedia, performing bench press exercises...

La siguiente página usa este archivo:

Uso global del archivo

Las wikis siguientes utilizan este archivo: