ModelPrésentéExterne

Ddpm Celebahq Finetuned Vintage Face 2epochs

This model was fine-tuned for 2 epochs on the CelebAHQ dataset to generate vintage-style face images.

Sourcehuggingface.co/naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs/tree/380d1902a27a1b1345a03a7457b93ce04d260743

TypeOtherModèle de basegoogle/ddpm-celebahq-256VersionRevision 380d190BClasse

Source du modèle

Type: Other
Taille du fichier: 434 MB
Modèle de base: google/ddpm-celebahq-256
Version: vRevision 380d190
Mis à jour: 31 oct. 2026
Téléchargements: 0
Source: Hugging Face

Description de la source

ddpm-celebahq-finetuned-vintage-face-2epochs

This model was fine-tuned for 2 epochs on the CelebAHQ dataset to generate vintage-style face images.

Denoising Evolution (Step 0 to 50)

The image below shows the generation process from pure noise (left) to the final face (right), captured every 10 steps.

Denoising Evolution

Usage

from diffusers import DDPMPipeline

pipeline = DDPMPipeline.from_pretrained('naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs')
image = pipeline(num_inference_steps=50).images[0]
image

Sources

1 source

Hugging FacePrincipalVersion 380d1902a27a1b1345a03a7457b93ce04d260743

huggingface.co/naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs/tree/380d1902a27a1b1345a03a7457b93ce04d260743

Vérifié 31 oct.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

1 artefact

unet/diffusion_pytorch_model.safetensors

safetensors · FP32 (unverified) · 434 MB · SHA-256 1708887c3e0f…9aa9 · Hugging Face

Download file

Extraits de sources

3 extraits

Readme16 aoûthuggingface.co/naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs

--- license: mit tags: - pytorch - diffusers - unconditional-image-generation - diffusion-models-class base_model: google/ddpm-celebahq-256 --- # ddpm-celebahq-finetuned-vintage-face-2epochs This model was fine-tuned for 2 epochs on the CelebAHQ dataset to generate vintage-style face images. ## Denoising Evolution (Step 0 to 50) The image below shows the generation process from pure noise (left) to the final face (right), captured every 10 steps. ![Denoising Evolution](https://huggingface.co/naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs/resolve/main/diffusion_evolution.png) ## Usage ```python from diffusers import DDPMPipeline pipeline = DDPMPipeline.from_pretrained('naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs') image = pipeline(num_inference_steps=50).images[0] image

Note31 oct.huggingface.co/naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs

Source context: 0 downloads · 0 likes · Pipeline unconditional-image-generation · Library diffusers · Repo naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs

Note16 aoûthuggingface.co/naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs

Source context: 4 downloads · 0 likes · Pipeline unconditional-image-generation · Library diffusers · Repo naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs