Consistency Decoder VAE by OpenAI v1.0 for SD 1.5

Consistency Decoder VAE by OpenAI - v1.0

OpenAi has decided to open source their consistency decoder vae
https://openai.com/blog/new-models-and-developer-products-announced-at-devday

Currently no support in Automatic1111, but for ComfyUI use this https://github.com/Jordach/comfy-consistency-vae

Description

initial version

FAQ

Comments (15)

harmonicdiffusionNov 7, 2023· 1 reaction

CivitAI

Interesting, I thought you told me not to post models such as this? Is there a clarification on that rule now? Is it allowed for everyone to do or just you?

eurotaku

Author

Nov 7, 2023· 4 reactions

which model are you talking about? just had a look at your models and the only comment i found was made on the t2i-adapters by h94, where i just asked you to mention the original creator of those models and include a link to the usage instructions. where exactly did i tell you to not post a certain model?

kuroro253Nov 7, 2023· 1 reaction

CivitAI

Any plans for an automatic1111 version?

eurotaku

Author

Nov 8, 2023· 2 reactions

you can already test it on this branch https://github.com/AUTOMATIC1111/stable-diffusion-webui/tree/consistency-dec

kuroro253Nov 8, 2023

@eurotaku Thank you

ShivaeNov 8, 2023

CivitAI

Please tell me how I can use it.

eurotaku

Author

Nov 8, 2023

either use the linked node in comfyui or this branch of automatic1111 https://github.com/AUTOMATIC1111/stable-diffusion-webui/tree/consistency-dec

ShivaeNov 8, 2023

@eurotakuI can't access the comfyUI node or load it in 1111, is there a solution?

zaadsatanNov 8, 2023

@eurotaku in this new branch I'm having this "MemoryError: bad allocation"

ShivaeNov 9, 2023· 1 reaction

@zaadsatan @zaadsatan city96/ComfyUI_ExtraModels: Support for miscellaneous image models. Currently supports: DiT, PixArt, T5 and a few custom VAEs (github.com ) give it a try

eurotaku

Author

Nov 9, 2023· 1 reaction

@zaadsatan might simply not be bugfree, yet, still awaiting merge into dev branch. you could ask directly on github, if someone can help you with that error

PiscaboNov 13, 2023· 1 reaction

CivitAI

Anything for SDXL?

d_A_v_I_dDec 2, 2023· 6 reactions

CivitAI

So apparently this thing wants to use 38 GB of vram when decoding a 1600x2160 image...

eurotaku

Author

Dec 4, 2023

wow, can it be tiled?

aimerabhiSep 20, 2024

CivitAI