Search results

where is the pre-trained VQGAN models provided by LDM ???

Status: Open.

#399 In CompVis/latent-diffusion;

· YZY-10 opened on Jun 5, 2025

text to image LDM

Status: Open.

#396 In CompVis/latent-diffusion;

· skuranuki opened on Mar 23, 2025

Fine-tuning of first_stage_model Weights in Pretrained LDMs

Status: Open.

#395 In CompVis/latent-diffusion;

· HONGcogml opened on Mar 16, 2025

where is txt2img.yaml?

Status: Open.

#394 In CompVis/latent-diffusion;

· lixinliu1995 opened on Mar 14, 2025

OOM When Training AutoencoderKL with 512x512 Inputs on 4x32GB V100s

Status: Open.

#393 In CompVis/latent-diffusion;

· joestitty opened on Feb 26, 2025

[Request] DDIM Inversion implementation

Status: Open.

#392 In CompVis/latent-diffusion;

· andreabosisio opened on Feb 6, 2025

Permission to use Figures from the paper

Status: Open.

#391 In CompVis/latent-diffusion;

· matemato opened on Jan 31, 2025

Questions about reconstruction and adversarial losses

Status: Open.

#390 In CompVis/latent-diffusion;

· lukau2357 opened on Jan 30, 2025

ffhq dataset

Status: Open.

#389 In CompVis/latent-diffusion;

· T02097 opened on Jan 22, 2025

SR training

Status: Open.

#386 In CompVis/latent-diffusion;

· cementwise opened on Nov 27, 2024

GAN Loss and Discriminator Loss are abnormal.

Status: Open.

#383 In CompVis/latent-diffusion;

· DragonisCV opened on Oct 24, 2024

About the kl-f4 config files

Status: Open.

#382 In CompVis/latent-diffusion;

· FantasticZihao opened on Oct 19, 2024