hololens/stable-diffusion-webui-depthmap-script

1## Changelog
2### 0.4.8
3 * Depth Anything V2 support, thanks [@graemeniedermayer](https://github.com/graemeniedermayer)!
4### 0.4.7
5 * Tiling mode
6 * Reduced VRAM consumption for Depth Anything, as well as for ZoeDepth k and nk
7 * Some bugfixes
8### 0.4.6
9 * Support for [Depth Anything](https://github.com/LiheYoung/Depth-Anything).
10### 0.4.5
11 * Preliminary support for [Marigold](https://marigoldmonodepth.github.io). [PR #385](https://github.com/thygate/stable-diffusion-webui-depthmap-script/pull/385).
12### 0.4.4
13 * Compatibility with stable-diffusion-webui 1.6.0
14### 0.4.3 video processing tab
15 * Added an option to process videos directly from a video file. This leads to better results than batch-processing individual frames of a video. Allows generating depthmap videos, that can be used in further generations as custom depthmap videos.
16 * UI improvements.
17 * Extra stereoimage generation modes - enable in extension settings if you want to use them.
18 * New stereoimage generation parameter - offset exponent. Setting it to 1 may produce more realistic outputs.
19### 0.4.2
20 * Added UI options for 2 additional rembg models.
21 * Heatmap generation UI option is hidden - if you want to use it, please activate it in the extension settings.
22 * Bugfixes.
23### 0.4.1 standalone mode
24 * Added ability to run DepthMap without WebUI. (Use main.py. Make sure all the dependencies are installed. The support is not feature-complete.)
25 * NormalMap generation
26### 0.4.0 large code refactor
27 * UI improvements
28 * Improved Batch from Directory, Clip and renormalize DepthMap
29 * Slightly changed the behaviour of various options
30 * Extension may partially work even if some of the dependencies are unmet
31
32### 0.3.12
33 * Fixed stereo image generation
34 * Other bugfixes
35### 0.3.11
36 * 3D model viewer (Experimental!)
37 * simple and fast (occluded) 3D mesh generation, support for equirectangular projection
38      (accurate results with ZoeDepth models only, no boost, no custom maps)
39 * default output format is now obj for inpainted mesh and simple mesh
40### 0.3.10 
41 * ZoeDepth support (with boost), 3 new models, best results so far
42 * better heatmap
43### 0.3.9
44 * use existing/custom depthmaps in output dir for batch mode
45 * custom depthmap support for single file
46 * wavefront obj output support for inpainted mesh (enabled in settings)
47 * option to generate all stereo formats at once
48 * bugfix: convert single channel input image to rgb
49 * renamed midas imports to fix conflict with deforum
50 * ui cleanup
51### 0.3.8 bugfix
52 * bugfix in remove background path
53### 0.3.7 new features
54 * [rembg](https://github.com/danielgatis/rembg) Remove Background [PR](https://github.com/thygate/stable-diffusion-webui-depthmap-script/pull/78) by [@graemeniedermayer](https://github.com/graemeniedermayer) merged
55 * setting to flip Left/Right SBS images
56 * added missing parameter for 3d inpainting (repeat_inpaint_edge)
57 * option to generate demo videos with mesh
58### 0.3.6 new feature
59 * implemented binary ply file format for the inpainted 3D mesh, big reduction in filesize and save/load times. 
60 * added progress indicators to the inpainting process 
61### 0.3.5 bugfix
62 * create path to 3dphoto models before download (see [issue](https://github.com/thygate/stable-diffusion-webui-depthmap-script/issues/76))
63### 0.3.4 new featues
64 * depth clipping option (original idea by [@Extraltodeus](https://github.com/Extraltodeus))
65 * by popular demand, 3D-Photo-Inpainting is now implemented
66 * generate inpainted 3D mesh (PLY) and videos of said mesh 
67### 0.3.3 bugfix and new midas models
68 * updated to midas 3.1, bringing 2 new depth models (the 512 one eats VRAM for breakfast!)
69 * fix Next-ViT dependency issue for new installs
70 * extension no longer clones repositories, all dependencies are now contained in the extension
71### 0.3.2 new feature and bugfixes
72 * several bug fixes for apple silicon and other machines without cuda
73 * NEW Stereo Image Generation techniques for gap filling by [@semjon00](https://github.com/semjon00) using polylines. (See [here](https://github.com/thygate/stable-diffusion-webui-depthmap-script/pull/56)) Significant improvement in quality.
74### 0.3.1 bugfix
75 * small speed increase for anaglyph creation
76 * clone midas repo before midas 3.1 to fix issue (see [here](https://github.com/thygate/stable-diffusion-webui-depthmap-script/issues/55#issue-1510266008))
77### 0.3.0 improved stereo image generation
78 * New improved technique for generating stereo images and balancing distortion between eyes by [@semjon00](https://github.com/semjon00) (See [here](https://github.com/thygate/stable-diffusion-webui-depthmap-script/pull/51))
79 * Substantial speedup of stereo image generation code using numba JIT
80### 0.2.9 new feature 
81 * 3D Stereo (side-by-side) and red/cyan anaglyph image generation.   
82    (Thanks to [@sina-masoud-ansari](https://github.com/sina-masoud-ansari) for the tip! Discussion [here](https://github.com/thygate/stable-diffusion-webui-depthmap-script/discussions/45))
83### 0.2.8 bugfix
84 * boost (pix2pix) now also able to compute on cpu
85 * res101 able to compute on cpu
86### 0.2.7 separate tab
87 * Depth Tab now available for easier stand-alone (batch) processing
88### 0.2.6 ui layout and settings
89 * added link to repo so more people find their way to the instructions.
90 * boost rmax setting
91### 0.2.5 bugfix
92 * error checking on model download (now with progressbar)
93### 0.2.4 high resolution depthmaps
94 * multi-resolution merging is now implemented, significantly improving results!
95 * res101 can now also compute on CPU
96### 0.2.3 bugfix
97 * path error on linux fixed
98### 0.2.2 new features
99 * added (experimental) support for AdelaiDepth/LeReS (GPU Only!)
100 * new option to view depthmap as heatmap
101 * optimised ui layout
102### 0.2.1 bugfix
103 * Correct seed is now used in filename and pnginfo when running batches. (see [issue](https://github.com/thygate/stable-diffusion-webui-depthmap-script/issues/35))
104### 0.2.0 upgrade
105 * the script is now an extension, enabling auto installation.
106### 0.1.9 bugfixes
107 * sd model moved to system memory while computing depthmap
108 * memory leak/fragmentation issue fixed
109 * recover from out of memory error
110### 0.1.8 new options
111 * net size can now be set as width and height, option to match input size, sliders now have the same range as generation parameters. (see usage below)
112 * better error handling
113### 0.1.7 bugfixes
114 * batch img2img now works (see [issue](https://github.com/thygate/stable-diffusion-webui-depthmap-script/issues/21#issuecomment-1306445056))
115 * generation parameters now only saved when enabled in settings
116 * model memory freed explicitly at end of script
117### 0.1.6 new option
118 * option to invert depthmap (black=near, white=far), as required by some viewers.
119### 0.1.5 bugfix
120 * saving as any format other than PNG now always produces an 8 bit, 3 channel RGB image. A single channel 16 bit image is only supported when saving as PNG. (see [issue](https://github.com/thygate/stable-diffusion-webui-depthmap-script/issues/15#issuecomment-1304909019))
121### 0.1.4 update
122 * added support for `--no-half`. Now also works with cards that don't support half precision like GTX 16xx. ([verified](https://github.com/thygate/stable-diffusion-webui-depthmap-script/issues/12#issuecomment-1304656398))
123### 0.1.3 bugfix
124 * bugfix where some controls where not visible (see [issue](https://github.com/thygate/stable-diffusion-webui-depthmap-script/issues/11#issuecomment-1304400537))
125### 0.1.2 new option
126 * network size slider. higher resolution depth maps (see usage below)
127### 0.1.1 bugfixes
128 * overflow issue (see [here](https://github.com/thygate/stable-diffusion-webui-depthmap-script/issues/10) for details and examples of artifacts)
129 * when not combining, depthmap is now saved as single channel 16 bit
130### 0.1.0
131 * initial version: script mode, supports generating depthmaps with 4 different midas models