Commit Graph

8174 Commits

Author SHA1 Message Date
layerdiffusion 018903ce2a fix kohya-hr 2024-08-02 00:37:14 -07:00
layerdiffusion 61ca3bc34f fix lora 2024-08-01 23:29:27 -07:00
layerdiffusion f6981339b0 predictor is a better name 2024-08-01 21:29:34 -07:00
layerdiffusion bc9977a305 UNet from Scratch
Now backend rewrite is about 50% finished.
Estimated finish is in 72 hours.
After that, many newer features will land.
2024-08-01 21:19:41 -07:00
lllyasviel e3522c8919 Update README.md 2024-08-01 16:05:36 -07:00
lllyasviel e015919632 Update README.md 2024-08-01 15:55:56 -07:00
lllyasviel 5f9e047301 Update README.md 2024-08-01 15:55:00 -07:00
layerdiffusion b3bd78289e resolve #915 2024-08-01 14:17:04 -07:00
layerdiffusion fec51bf2dd ling 2024-08-01 13:07:42 -07:00
bluelovers 37492057e5 Update forge_freeu.py (#718)
for `sd-webui-bilingual-localization`
2024-08-01 12:55:26 -07:00
Dan Weiss 0207eec2cd Add pasting fields into Latent Modifier settings (#624) 2024-08-01 12:55:11 -07:00
continue revolution 5192e912ab GroupNorm patcher (#593)
* add gn wrapper and corresponding patcher

* add gn wrapper and corresponding patcher
2024-08-01 12:53:27 -07:00
altoiddealer 0eea1acc6e Restore '/controlnet/control_types' API endpoint (#912)
Restores the '/controlnet/control_types' API endpoint, which is immensely useful for anyone using ControlNet via the API

## Description

I recently opened an Issue on the main ControlNet extension repo Mikubill/sd-webui-controlnet#2737 suggesting that they add a new API endpoint to allow users to retrieve filtered data based on a Control Type, just like in the UI.

I was both shocked and immensely disappointed when they finally replied, stating that the endpoint does already exist!

I understand that Forge is a massive overhaul to A1111, so perhaps this aspect was removed to get everything working, and then just never reimplemented.

Whatever the case, this endpoint is truly amazing for using ControlNet via API.  With only the 'models' and 'modules' endpoints, how the heck is someone to make a dynamic script?  They would essentially have to take a fat chunk of existing ControlNet code, plus these few added functions, just to filter the data appropriately.

I'm an amateur coder, at best, however I'm quite confident about this implementation.

This uses your existing functions as best as possible, I believe, including your filter list and the check for currently loaded SD model version.

Please merge this.

Thank you

## Screenshots/videos:

<img width="1136" alt="Restored" src="https://github.com/lllyasviel/stable-diffusion-webui-forge/assets/1613484/8996c3f2-27be-4405-b0cd-7f05f3eaa2d2">

[response_1714160176770.json](https://github.com/lllyasviel/stable-diffusion-webui-forge/files/15134692/response_1714160176770.json)

## Checklist:

- [X] I have read [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
- [X] I have performed a self-review of my own code
- [X] My code follows the [style guidelines](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing#code-style)
- [X] My code passes [tests](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Tests)
2024-08-01 12:48:30 -07:00
layerdiffusion 4d1be42975 Intergrate CLIP 2024-08-01 12:27:20 -07:00
layerdiffusion af0b04cc16 store huggingface vars in VAE 2024-07-31 21:40:18 -07:00
layerdiffusion 3079b81547 make attn func name more technically correct 2024-07-31 21:35:19 -07:00
layerdiffusion 3fb9d5a85c fix vae output layer weight cannot cast 2024-07-31 21:20:56 -07:00
layerdiffusion 0d079a846d Intergrate Native AutoEncoderKL 2024-07-31 21:10:19 -07:00
layerdiffusion 2c3afff371 gradio==4.40.0
all basic UIs tested
2024-07-31 19:04:02 -07:00
layerdiffusion f052fabd4d make model guess a function that can be patched 2024-07-30 17:26:49 -06:00
layerdiffusion c8156fcf41 rework model loader and configs 2024-07-30 13:27:26 -06:00
layerdiffusion 40dd61ba6c improve vae key mapping 2024-07-30 09:23:58 -06:00
layerdiffusion 3289ccb53f add vae configs 2024-07-30 08:55:22 -06:00
layerdiffusion dc62b0d2d7 begin to use new vae impl 2024-07-30 08:43:14 -06:00
layerdiffusion abd4d4d83d unify cast name 2024-07-30 08:42:51 -06:00
layerdiffusion 9a48c9eff3 rename state_dict method to make it clear 2024-07-30 08:05:36 -06:00
layerdiffusion 9cb69baf9f Implement VAE for new backend 2024-07-29 22:26:32 -06:00
layerdiffusion e6e18f7edb Update .gitignore 2024-07-29 17:55:44 -06:00
layerdiffusion 50da83d985 upgrade diffusers 2024-07-29 17:33:05 -06:00
layerdiffusion 3bc9402de9 ling 2024-07-29 11:48:55 -06:00
layerdiffusion 68b672493a implement attention for new backend 2024-07-29 11:46:16 -06:00
layerdiffusion 99fcb35506 rename 2024-07-29 11:29:29 -06:00
layerdiffusion c4f52d8ffb add args for new backend 2024-07-29 11:27:58 -06:00
layerdiffusion 5d291c28ad implement args for new backend 2024-07-29 11:22:20 -06:00
layerdiffusion 1b2610db3e implement stream in new backend 2024-07-29 11:16:59 -06:00
layerdiffusion 9793b4be0f implement operations from scratch 2024-07-29 10:59:16 -06:00
layerdiffusion 6b163843fc add backend folder 2024-07-29 10:37:18 -06:00
layerdiffusion 4a9c8f32ee remove train tab
This tab has been broken since 6 months ago and no one even creates an issue for it ; this indicates no one uses it.
Also just tried original webui Train tab and it seems also broken even in Auto's repo.
so we remove it to make room for new tabs and new features.
2024-07-29 10:02:43 -06:00
layerdiffusion c3e17f05f3 fix #880 2024-07-29 09:22:44 -06:00
lllyasviel 0bfc3beb36 Update README.md 2024-07-29 08:20:13 -06:00
layerdiffusion 37386592ad version 2024-07-28 08:08:28 -06:00
layerdiffusion 918c6af162 upgrade js canvas for #881 2024-07-28 08:07:37 -06:00
layerdiffusion f3926ee3b7 resolve t2i upscale button #882 #874 2024-07-28 07:59:53 -06:00
layerdiffusion 2f87f123b2 less aggressive clip skip
to make CivitAI pony image meta works better
2024-07-27 13:23:39 -07:00
layerdiffusion 6eb23c6d09 fix #861 2024-07-27 07:52:20 -07:00
layerdiffusion 7e31721803 fix #861 2024-07-27 07:50:59 -07:00
layerdiffusion 3ba632b64b version 2024-07-27 06:54:05 -07:00
layerdiffusion f94bcae7b0 fix img2img batch upload 2024-07-27 06:53:37 -07:00
layerdiffusion d4e7639233 sync change log 2024-07-27 06:47:04 -07:00
layerdiffusion 04c6ab68bb 1.10.1 2024-07-27 06:39:58 -07:00