aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Merge pull request #5718 from space-nuko/feature/save-hypernetwork-hashAUTOMATIC11112022-12-242-2/+36
|\ | | | | Save hypernetwork hash and fix hypernetwork parameter restoring
| * Fix commentspace-nuko2022-12-131-1/+1
| |
| * Correctly restore default hypernetwork strengthspace-nuko2022-12-131-0/+3
| |
| * Correctly restore hypernetwork from hashspace-nuko2022-12-131-0/+30
| |
| * Save hypernetwork hash in infotextspace-nuko2022-12-131-2/+3
| |
* | rename the option for img2img latent upscaleAUTOMATIC2022-12-242-2/+2
| |
* | Merge pull request #5521 from AndrewRyanChama/ryan/img2imglatentscaleAUTOMATIC11112022-12-242-2/+6
|\ \ | | | | | | Add latent upscale option to img2img
| * | Add latent upscale option to img2imgAndrew Ryan2022-12-082-2/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Recently, the option to do latent upscale was added to txt2img highres fix. This feature runs by scaling the latent sample of the image, and then running a second pass of img2img. But, in this edition of highres fix, the image and parameters cannot be changed between the first pass and second pass. We might want to do a fixup in img2img before doing the second pass, or might want to run the second pass at a different resolution. This change adds the option for img2img to perform its upscale in latent space, rather than image space, giving very similar results to highres fix with latent upscale. The result is not exactly the same because there is an additional latent -> decoder -> image -> encoder -> latent that won't happen in highres fix, but this conversion has relatively small losses
* | | Merge pull request #5838 from aliencaocao/fix_gradio_pilAUTOMATIC11112022-12-241-0/+1
|\ \ \ | | | | | | | | Dirty fix for missing PIL supported file extensions
| * | | Fix PIL being imported before its installed (for new users only)Billy Cao2022-12-182-1/+1
| | | |
| * | | Dirty fix for missing PIL supported file extensionsBilly Cao2022-12-181-0/+1
| | | |
* | | | Merge pull request #5747 from yuvalabou/singleton-comparisonAUTOMATIC11112022-12-243-5/+9
|\ \ \ \ | | | | | | | | | | Format singleton comparisons
| * | | | Correct singleton comparisonsYuval Aboulafia2022-12-143-5/+9
| | |_|/ | |/| |
* | | | Merge pull request #5873 from philpax/override-settings-restore-afterwardsAUTOMATIC11112022-12-241-7/+10
|\ \ \ \ | | | | | | | | | | feat(api): add override_settings_restore_afterwards
| * | | | feat(api): add override_settings_restore_afterwardsPhilpax2022-12-201-13/+16
| |/ / /
* | | | Merge pull request #5753 from calvinballing/masterAUTOMATIC11112022-12-2416-68/+68
|\ \ \ \ | | | | | | | | | | Fix various typos
| * | | | Fix various typosJim Hays2022-12-1516-68/+68
| |/ / /
* | | | Merge pull request #5589 from MrCheeze/better-special-model-supportAUTOMATIC11112022-12-243-8/+12
|\ \ \ \ | | | | | | | | | | Better support for 2.0-inpainting and 2.0-depth special models
| * | | | unconditionally set use_ema=False if value not specified (True never worked, ↵MrCheeze2022-12-111-1/+3
| | | | | | | | | | | | | | | | | | | | and all configs except v1-inpainting-inference.yaml already correctly set it to False)
| * | | | fix support for 2.0 inpainting model while maintaining support for 1.5 ↵MrCheeze2022-12-102-2/+2
| | | | | | | | | | | | | | | | | | | | inpainting model
| * | | | unload depth model if medvram/lowvram enabledMrCheeze2022-12-101-5/+7
| |/ / /
* | | | add an option for img2img background colorAUTOMATIC2022-12-244-2/+14
| | | |
* | | | add blendmodes to requirements_versions, remove aenum as it's already ↵AUTOMATIC2022-12-242-1/+1
| | | | | | | | | | | | | | | | required by blendmodes
* | | | Merge pull request #5644 from ThereforeGames/masterAUTOMATIC11112022-12-242-3/+8
|\ \ \ \ | | | | | | | | | | Improve img2img color correction by performing a luminosity blend
| * | | | Update requirements.txtThereforeGames2022-12-111-0/+2
| | | | |
| * | | | Delete venv/Lib/site-packages directoryThereforeGames2022-12-1117-15666/+0
| | | | |
| * | | | Improve color correction with luminosity blendThereforeGames2022-12-111-3/+6
| | | | |
| * | | | Add files via uploadThereforeGames2022-12-1117-0/+15666
| |/ / /
* | | | Merge pull request #5808 from stysmmaker/patch/fix-fnt-sizeAUTOMATIC11112022-12-241-7/+16
|\ \ \ \ | | | | | | | | | | Prevent overlapping in X/Y plot by changing font size
| * | | | fix: Modify font size when unable to fit in plotMMaker2022-12-171-7/+16
| |/ / / | | | | | | | | This prevents scenarios where text without line breaks will start overlapping with each other when generating X/Y plots. This is most evident when generating X/Y plots with checkpoints, as most don't contain spaces and sometimes include extra information such as the epoch, making it extra long.
* | | | Merge pull request #5814 from timntorres/5802-save-upscaler-to-filenameAUTOMATIC11112022-12-242-1/+8
|\ \ \ \ | | | | | | | | | | Add option to save upscaler to filename suffix in extras tab.
| * | | | Update OptionInfo to match preexisting option.timntorres2022-12-171-1/+1
| | | | |
| * | | | Add option to include upscaler name in filename.timntorres2022-12-172-2/+4
| | | | |
| * | | | Add upscaler name as a suffix.timntorres2022-12-171-1/+6
| | |_|/ | |/| |
* | | | Merge pull request #4684 from simcop2387/fix-extension-dockerAUTOMATIC11112022-12-241-1/+14
|\ \ \ \ | | | | | | | | | | Fix docker tmp/ and extensions/ handling for docker.
| * | | | Fix docker tmp/ and extensions/ handling for docker. might also work for ↵Ryan Voots2022-11-131-1/+14
| | | | | | | | | | | | | | | | | | | | symlinks
* | | | | Merge pull request #5840 from stysmmaker/feat/xy-plot-new-axesAUTOMATIC11112022-12-241-1/+43
|\ \ \ \ \ | | | | | | | | | | | | Add upscale latent, VAE, styles as new axis options to X/Y plot
| * | | | | feat: Add upscale latent, VAE, styles to X/Y plotMMaker2022-12-181-1/+43
| | |_|/ / | |/| | | | | | | | Adds upscale latent space for hires., VAE, and Styles as new axis options to the X/Y plot.
* | | | | eliminate duplicated codeAUTOMATIC2022-12-241-17/+14
| | | | | | | | | | | | | | | | | | | | add an option to samplers for skipping next to last sigma
* | | | | Merge pull request #5797 from mcmonkey4eva/dpm2-a-fixAUTOMATIC11112022-12-241-0/+6
|\ \ \ \ \ | | | | | | | | | | | | Add a workaround patch for DPM2 a issue
| * | | | | fix dpm2 in img2img as wellAlex "mcmonkey" Goodwin2022-12-191-0/+3
| | | | | |
| * | | | | apply to DPM2 (non-ancestral) as wellAlex "mcmonkey" Goodwin2022-12-161-1/+1
| | | | | |
| * | | | | Add a workaround patch for DPM2 a issueAlex "mcmonkey" Goodwin2022-12-161-0/+3
| |/ / / / | | | | | | | | | | | | | | | DPM2 a and DPM2 a Karras samplers are both affected by an issue described by https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/3483 and can be resolved by a workaround suggested by the k-diffusion author at https://github.com/crowsonkb/k-diffusion/issues/43#issuecomment-1305195666
* | | | | Merge pull request #5894 from florianchrometz/patch-1AUTOMATIC11112022-12-241-0/+1
|\ \ \ \ \ | | | | | | | | | | | | Set httpcore version in requirements - fixes #4833
| * | | | | Set httpcore version in requirements - fixes #4833Florian Chrometz2022-12-201-0/+1
| |/ / / /
* | | | | Merge pull request #5810 from brkirch/fix-training-mpsAUTOMATIC11112022-12-242-6/+15
|\ \ \ \ \ | | | | | | | | | | | | Training fixes for MPS
| * | | | | Add attributes used by MPSbrkirch2022-12-171-6/+6
| | | | | |
| * | | | | Add numpy fix for MPS on PyTorch 1.12.1brkirch2022-12-171-0/+9
| |/ / / / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When saving training results with torch.save(), an exception is thrown: "RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead." So for MPS, check if Tensor.requires_grad and detach() if necessary.
* | | | | Merge pull request #5796 from brkirch/invoke-fixAUTOMATIC11112022-12-241-4/+6
|\ \ \ \ \ | | | | | | | | | | | | Improve InvokeAI cross attention reliability and speed when using MPS for large images
| * | | | | Use other MPS optimization for large q.shape[0] * q.shape[1]brkirch2022-12-211-4/+6
| |/ / / / | | | | | | | | | | | | | | | | | | | | | | | | | Check if q.shape[0] * q.shape[1] is 2**18 or larger and use the lower memory usage MPS optimization if it is. This should prevent most crashes that were occurring at certain resolutions (e.g. 1024x1024, 2048x512, 512x2048). Also included is a change to check slice_size and prevent it from being divisible by 4096 which also results in a crash. Otherwise a crash can occur at 1024x512 or 512x1024 resolution.
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-05 11:14:00 +0000