Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-11 15:28:43 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix infotext wrapping

Browse Source
This commit is contained in:
Vladimir Mandic
2023-12-04 09:22:14 -05:00
parent 099188a8cd
commit 3d971d7bbf
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+5 -5
View File
@@ -1,15 +1,11 @@
# Change Log for SD.Next
## Update for 2023-12-01
## Update for 2023-12-04
What's new? Native video in SD.Next via both **AnimateDiff** and **Stable-Video-Diffusion** - and including native MP4 encoding and smooth video outputs out-of-the-box, not just animated-GIFs.
Also new is support for **SDXL-Turbo** as well as new **Kandinsky 3** models and cool latent correction via **HDR controls** for any *txt2img* workflows, best-of-class **SDXL model merge** using full ReBasin methods and further mobile UI optimizations.
- **Diffusers**
- **HDR latent control**, based on [article](https://huggingface.co/blog/TimothyAlexisVass/explaining-the-sdxl-latent-space#long-prompts-at-high-guidance-scales-becoming-possible)
- in *Advanced* params
- allows control of *latent clamping*, *color centering* and *range maximimization*
- supported by *XYZ grid*
- **IP adapter**
- lightweight native implementation of T2I adapters which can guide generation towards specific image style
- supports most T2I models, not limited to SD 1.5
@@ -23,6 +19,10 @@ Also new is support for **SDXL-Turbo** as well as new **Kandinsky 3** models and
- for video saving support, see video support section
- can be combined with IP-Adapter for even better results!
- for AnimateDiff support in *Original* backend, use standard *AnimateDiff* extension
- **HDR latent control**, based on [article](https://huggingface.co/blog/TimothyAlexisVass/explaining-the-sdxl-latent-space#long-prompts-at-high-guidance-scales-becoming-possible)
- in *Advanced* params
- allows control of *latent clamping*, *color centering* and *range maximimization*
- supported by *XYZ grid*
- [SD21 Turbo](https://huggingface.co/stabilityai/sd-turbo) and [SDXL Turbo](<https://huggingface.co/stabilityai/sdxl-turbo>) support
- just set CFG scale (0.0-1.0) and steps (1-3) to a very low value
- compatible with original StabilityAI SDXL-Turbo or any of the newer merges
javascript/sdnext.css
+1 -1
View File
@@ -95,7 +95,7 @@ div#extras_scale_to_tab div.form{ flex-direction: row; }
#img2img_sketch, #img2maskimg, #inpaint_sketch { overflow: overlay !important; resize: auto; background: var(--panel-background-fill); z-index: 5; }
.image-buttons button{ min-width: auto; }
.infotext { overflow-wrap: break-word; line-height: 1.5em; }
.infotext > p { padding-left: 1em; text-indent: -1em; white-space: pre; text-wrap: pretty; }
.infotext > p { padding-left: 1em; text-indent: -1em; white-space: pre-wrap; }
.tooltip { display: block; position: fixed; top: 1em; right: 1em; padding: 0.5em; background: var(--input-background-fill); color: var(--body-text-color); border: 1pt solid var(--button-primary-border-color);
width: 22em; min-height: 1.3em; font-size: 0.8em; transition: opacity 0.2s ease-in; pointer-events: none; opacity: 0; z-index: 999; }
.tooltip-show { opacity: 0.9; }