Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-18 16:54:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

add embedding convert notes

Browse Source
This commit is contained in:
Vladimir Mandic
2024-01-27 15:39:54 -05:00
parent a614170f50
commit ebdc2144a8
2 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+7 -2
View File
@@ -31,8 +31,9 @@ Another big release, highlights being:
- Complete **Face** module
implements all variations of **FaceID**, **FaceSwap** and latest **PhotoMaker** and **InstantID**
- Much enhanced **IPAdapter** modules
- Brand new **intelligent masking**, manual or automatic
Using ML models (object removal, background removal, segmentation, etc.) and with live previews
- Brand new **Intelligent masking**, manual or automatic
Using ML models (*LAMA* object removal, *REMBG* background removal, *SAM* segmentation, etc.) and with live previews
Granular blur, erode and dilate controls
Plus welcome additions to **UI performance, usability and accessibility** and flexibility of deployment
And it also includes fixes for all reported issues so far
@@ -175,6 +176,10 @@ As of this release, default backend is set to **diffusers** as its more feature
- using built-in NNCF model compression, you can reduce the size of your models significantly
example: up to 3.4GB of VRAM saved for SD-XL model!
- see [wiki](https://github.com/vladmandic/automatic/wiki/Model-Compression-with-NNCF) for details
- **embeddings**
you can now use sd 1.5 embeddings with your sd-xl models!, thanks @AI-Casanova
conversion is done on-the-fly, is completely transparent and result is an approximation of embedding
to enable: settings->extra networks->auto-convert embeddings
- **offline deployment**: allow deployment without git clone
for example, you can now deploy a zip of the sdnext folder
- **latent upscale**: updated latent upscalers (some are new)
modules/shared.py
+1 -1
View File
@@ -432,7 +432,6 @@ options_templates.update(options_section(('diffusers', "Diffusers Settings"), {
"diffusers_force_zeros": OptionInfo(False, "Force zeros for prompts when empty", gr.Checkbox, {"visible": False}),
"diffusers_aesthetics_score": OptionInfo(False, "Require aesthetics score"),
"diffusers_pooled": OptionInfo("default", "Diffusers SDXL pooled embeds", gr.Radio, {"choices": ['default', 'weighted']}),
"diffusers_convert_embed": OptionInfo(False, "Auto-convert SD 1.5 Embeddings to SDXL ", gr.Checkbox, {"visible": True}),
"huggingface_token": OptionInfo('', 'HuggingFace token'),
}))
@@ -681,6 +680,7 @@ options_templates.update(options_section(('extra_networks', "Extra Networks"), {
"extra_networks_sep2": OptionInfo("<h2>Extra networks general</h2>", "", gr.HTML),
"extra_network_skip_indexing": OptionInfo(False, "Build info on first access", gr.Checkbox),
"extra_networks_default_multiplier": OptionInfo(1.0, "Default multiplier for extra networks", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
"diffusers_convert_embed": OptionInfo(False, "Auto-convert SD 1.5 embeddings to SDXL ", gr.Checkbox, {"visible": backend==Backend.DIFFUSERS}),
"extra_networks_sep3": OptionInfo("<h2>Extra networks settings</h2>", "", gr.HTML),
"extra_networks_styles": OptionInfo(True, "Show built-in styles"),
"lora_preferred_name": OptionInfo("filename", "LoRA preffered name", gr.Radio, {"choices": ["filename", "alias"]}),