[bug]: 2.3.0 - VAE showing up in Models List

[ShaguarWKL]

Is there an existing issue for this?

• [X] I have searched the existing issues

OS

Windows

GPU

cuda

VRAM

No response

What happened?

blessed and istein knows about this. Just posting this up for issue tracking.

Screenshots

Additional context

No response

Contact Details

No response

[lstein]

Thanks for the report.

[psychedelicious]

I've downloaded the trinart vae and cannot get it to show up in the model manager at all - cannot reproduce this. Can you please post your configs/models.yaml file?

[ShaguarWKL]

I've downloaded the trinart vae and cannot get it to show up in the model manager at all - cannot reproduce this. Can you please post your configs/models.yaml file?

I've deleted that install. Let me do a new clean install and download all of that and repost it. Will revert back.

[ShaguarWKL]

RC6. Will check RC7 later. Just noticed it.

YAML after install

# This file describes the alternative machine learning models
# available to InvokeAI script.
#
# To add a new model, follow the examples below. Each
# model requires a model config file, a weights file,
# and the width and height of the images it
# was trained on.
stable-diffusion-1.5:
  description: Stable Diffusion version 1.5 weight file (4.27 GB)
  repo_id: runwayml/stable-diffusion-v1-5
  format: diffusers
  vae:
    repo_id: stabilityai/sd-vae-ft-mse
  default: true
inpainting-1.5:
  description: RunwayML SD 1.5 model optimized for inpainting (4.27 GB)
  repo_id: runwayml/stable-diffusion-inpainting
  format: diffusers
  vae:
    repo_id: stabilityai/sd-vae-ft-mse
dreamlike-diffusion-1.0:
  description: An SD 1.5 model fine tuned on high quality art by dreamlike.art
  repo_id: dreamlike-art/dreamlike-diffusion-1.0
  format: diffusers
  vae:
    repo_id: stabilityai/sd-vae-ft-mse
dreamlike-photoreal-2.0:
  description: A photorealistic model trained on 768 pixel images based on SD 1.5
    (2.13 GB)
  repo_id: dreamlike-art/dreamlike-photoreal-2.0
  format: diffusers
stable-diffusion-2.1-768:
  description: Stable Diffusion version 2.1 diffusers model, trained on 768 pixel
    images (5.21 GB)
  repo_id: stabilityai/stable-diffusion-2-1
  format: diffusers
stable-diffusion-2.1-base:
  description: Stable Diffusion version 2.1 diffusers base model, trained on 512 pixel
    images (5.21 GB)
  repo_id: stabilityai/stable-diffusion-2-1-base
  format: diffusers
openjourney-4.0:
  description: An SD 1.5 model fine tuned on Midjourney images by PromptHero - include
    "mdjrny-v4 style" in your prompts (2.13 GB)
  repo_id: prompthero/openjourney
  format: diffusers
  vae:
    repo_id: stabilityai/sd-vae-ft-mse
nitro-diffusion-1.0:
  description: A SD 1.5 model trained on three artstyles - prompt with "archer style",
    "arcane style" and/or "modern disney style" (2.13 GB)
  repo_id: nitrosocke/Nitro-Diffusion
  format: diffusers
  vae:
    repo_id: stabilityai/sd-vae-ft-mse
trinart-2.0:
  description: An SD model finetuned with ~40,000 assorted high resolution manga/anime-style
    pictures (2.13 GB)
  repo_id: naclbit/trinart_stable_diffusion_v2
  format: diffusers
  vae:
    repo_id: stabilityai/sd-vae-ft-mse
trinart-characters-2_0:
  description: An SD model finetuned with 19.2M anime/manga style images (ckpt version)
    (4.27 GB)
  repo_id: naclbit/trinart_derrida_characters_v2_stable_diffusion
  format: ckpt
  width: 512
  height: 512
  weights: models\ldm\stable-diffusion-v1\derrida_final.ckpt
  config: C:\Users\warre\Downloads\RC6\configs\stable-diffusion\v1-inference.yaml
  vae: models\ldm\stable-diffusion-v1\autoencoder_fix_kl-f8-trinart_characters.ckpt
ft-mse-improved-autoencoder-840000:
  description: StabilityAI improved autoencoder fine-tuned for human faces. Improves
    legacy .ckpt models (335 MB)
  repo_id: stabilityai/sd-vae-ft-mse-original
  format: ckpt
  width: 512
  height: 512
  weights: models\ldm\stable-diffusion-v1\vae-ft-mse-840000-ema-pruned.ckpt
  config: C:\Users\warre\Downloads\RC6\configs\stable-diffusion\VAE\default
trinart_vae:
  description: Custom autoencoder for trinart_characters for legacy .ckpt models only
    (335 MB)
  repo_id: naclbit/trinart_characters_19.2m_stable_diffusion_v1
  format: ckpt
  width: 512
  height: 512
  weights: models\ldm\stable-diffusion-v1\autoencoder_fix_kl-f8-trinart_characters.ckpt
  config: C:\Users\warre\Downloads\RC6\configs\stable-diffusion\VAE\trinart

[github-actions[bot]]

There has been no activity in this issue for 14 days. Please reply with a comment to keep the issue open. We recommend testing with the latest release to make sure it hasn't been already fixed.

[psychedelicious]

@lstein I'm not sure how to approach this. The offending models.yaml is provided in a comment above

[github-actions[bot]]

There has been no activity in this issue for 14 days. If this issue is still being experienced, please reply with an updated confirmation that the issue is still being experienced with the latest release.