Age | Commit message (Collapse) | Author | Lines | |
---|---|---|---|---|
2022-10-19 | face detection algo, configurability, reusability | captin411 | -136/+230 | |
Try to move the crop in the direction of a face if it is present More internal configuration options for choosing weights of each of the algorithm's findings Move logic into its module | ||||
2022-10-20 | align ui.py imports with upstream | discus0434 | -19/+18 | |
2022-10-20 | update | discus0434 | -9/+11 | |
2022-10-20 | update | discus0434 | -31/+44 | |
2022-10-20 | default to ignore existing captions | DepFA | -1/+1 | |
2022-10-20 | pass preprocess_txt_action param | DepFA | -3/+3 | |
2022-10-20 | link existing txt option | DepFA | -0/+2 | |
2022-10-20 | add existing caption file handling | DepFA | -8/+24 | |
2022-10-20 | reorder create_hypernetwork params | DepFA | -1/+1 | |
2022-10-20 | pass overwrite old flag | DepFA | -2/+2 | |
2022-10-20 | split learn rates | DepFA | -2/+2 | |
2022-10-20 | allow overwrite old embedding | DepFA | -2/+3 | |
2022-10-20 | allow overwrite old hn | DepFA | -2/+3 | |
2022-10-20 | change html output | DepFA | -1/+1 | |
2022-10-19 | Don't compute latent mask if were not using it. Also added support for fixed ↵ | random_thoughtss | -27/+49 | |
highres_fix generation. | ||||
2022-10-19 | added support for ddim img2img | random_thoughtss | -0/+6 | |
2022-10-19 | Fixed copying mistake | random_thoughtss | -54/+25 | |
2022-10-19 | Added support for RunwayML inpainting model | random_thoughtss | -15/+293 | |
2022-10-19 | fix entropy point calculation | captin411 | -15/+19 | |
2022-10-19 | update ui with extra training options | DepFA | -2/+9 | |
2022-10-19 | update training header text | DepFA | -1/+1 | |
2022-10-19 | generation_parameters_copypaste.py: fix indent | Mackerel | -2/+2 | |
2022-10-19 | Send empty prompts as valid generation parameter | Vladimir Repin | -3/+0 | |
2022-10-19 | Infotext saves more specific hypernet name. | timntorres | -1/+1 | |
2022-10-19 | Added a bit of padding to the left | Alexandre Simard | -1/+1 | |
2022-10-19 | Update ui.py | Alexandre Simard | -4/+9 | |
2022-10-19 | fix for #3086 failing to load any previous hypernet | discus0434 | -32/+28 | |
2022-10-19 | fix for #3086 failing to load any previous hypernet | AUTOMATIC | -32/+28 | |
2022-10-19 | Update ui.py | DepFA | -1/+1 | |
2022-10-20 | Merge branch 'AUTOMATIC1111:master' into master | discus0434 | -18/+45 | |
2022-10-19 | Merge pull request #3086 from discus0434/master | AUTOMATIC1111 | -21/+77 | |
Add settings for multi-layer structure hypernetworks | ||||
2022-10-19 | enable to write layer structure of hn himself | discus0434 | -1/+5 | |
2022-10-19 | layer options moves into create hnet ui | discus0434 | -38/+45 | |
2022-10-19 | UI changes for focal point image cropping | captin411 | -1/+3 | |
2022-10-19 | Add auto focal point cropping to Preprocess images | captin411 | -5/+146 | |
This algorithm plots a bunch of points of interest on the source image and averages their locations to find a center. Most points come from OpenCV. One point comes from an entropy model. OpenCV points account for 50% of the weight and the entropy based point is the other 50%. The center of all weighted points is calculated and a bounding box is drawn as close to centered over that point as possible. | ||||
2022-10-19 | fix for broken checkpoint merger | AUTOMATIC | -1/+4 | |
2022-10-19 | Fix typo in prompt_parser.py | Ikko Ashimine | -1/+1 | |
assoicated -> associated | ||||
2022-10-19 | Merge branch 'master' into test_resolve_conflicts | MalumaDev | -29/+254 | |
2022-10-19 | Merge branch 'master' into hot-reload-javascript | AUTOMATIC1111 | -151/+529 | |
2022-10-19 | Predictable long operation check for time estimation | Anastasius | -1/+1 | |
2022-10-19 | Estimated time displayed if jobs take more 60 sec | Anastasius | -5/+12 | |
2022-10-19 | Added time left estimation | Anastasius | -1/+13 | |
2022-10-19 | Remove wrong self reference in CUDA support for invokeai | Cheka | -1/+1 | |
2022-10-19 | Merge branch 'master' into master | discus0434 | -3/+4 | |
2022-10-19 | Use training width/height when training hypernetworks. | Silent | -2/+4 | |
2022-10-19 | Merge branch 'master' into master | discus0434 | -11/+210 | |
2022-10-19 | Merge remote-tracking branch 'origin/api' | AUTOMATIC | -8/+185 | |
2022-10-19 | more careful loading of model weights (eliminates some issues with ↵ | AUTOMATIC | -3/+25 | |
checkpoints that have weird cond_stage_model layer names) | ||||
2022-10-19 | call sampler by name | arcticfaded | -8/+9 | |
2022-10-19 | Image browser improved | yfszzx | -62/+80 | |