add k_dpmpp_2_a and k_dpmpp_2 solvers options #1389
Conversation
|
If we are prioritizing the 🧨diffusers migration for the next release, please hold off on merging this (and any other sampler changes) until after we get the diffusers backend in place. (#1384 and related.) After that, I expect the preferred way to use DPM++ solvers will be via huggingface/diffusers#1132 |
|
From what I understand in the PR, the migration to diffusers is in a pretty raw state, isn't it? I don't think it's too much of a change to worry about, unless the change to diffusers will happen in the following 2-3 days vs. having the options to test if the solvers help. |
|
Granted, this PR doesn't add much in the way of code that will make more work for the diffusers port. It adds some entries to some lists to allow Invoke access to more functions implemented in k-diffusion. But I'm not sure yet to what extent a diffusers-based pipeline will support direct use of k-diffusion, and if it doesn't then access to those samplers is something we'll have to walk back. At least until we figure out how to support them (and whether supporting k-diffusion and diffusers-provided methods is worth the effort, given how much overlap there will be between the two). |
|
Sounds like the move to diffusers is indeed very raw, if there are so many unknowns. Maybe by the time it's ready, there's already something new to go with instead. Sounds a bit too early for a code freeze, but anyways there's the option if anyone wants to test it. |
|
I've read through the crowson merge conversation but the main use case is supporting DPM-Solver. Will we see concrete gains in performance and/or image quality, or is this future proofing the repo against improvements that follow? Related question: what are the advantages to using the DPM-Solver++ module? I see there is a request to AUTOMATIC to incorporate it, and I imagine they will soon if not already. If it is a real improvement, then I'd consider importing it now. |
|
Another comment is that we are currently using @Birch-san 's "mps" fork of the k-diffusion repo, and he seems to have brought the dpmpp solvers in. Hopefully he can fix the black screen problem. |
|
😕 dpmpp samplers worked for me without any changes. I'm running pytorch nightly; that might be the difference? also: I rebase that mps branch whenever k-diffusion changes. if you have those samplers you're probably up-to-date, but be sure to compare what you have locally with what's in GitHub.
@keturn supported fully: |
|
@lstein DPM++ Solvers were merged to Auto's repo 3 days ago (AUTOMATIC1111/stable-diffusion-webui#4304). The main benefit of the new version of the solvers is producing high quality results at much lower steps number (some examples in the link above). @Birch-san great work! I was testing with a manually updated version of k-diffusers, before you updated the code, but I'll now test it again rebasing to your repo and update Pytorch to see if the issues are fixed! |
@lstein high-quality results in as few as 5 sampler steps: |
|
there's also an official (i.e. non-k-diffusion) implementation of DMP-Solver++. it can be integrated into a CompVis repo like so: |
|
Just wanna say I applied this patch a few days ago and the new samplers are pretty amazing. Lots of my prompts are coherent in 5-10 steps. It's a fairly clean change too, would love to see this merged |
|
@lstein I'm setting the PR as ready for review now, I think it's worth adding these options for further testing, but it seems to be working fine! |
|
On M1 Max I needed to do some other stuff to get it running: Update sampling.py in my miniconda3 env to https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/sampling.py Installed torchsde via pip I think I might have tweaked something else too, can't remember. I can now generate using k_dpmpp_2 and k_dpmpp_2_a in the CLI. However I can't work out how to get it to show in the webui - I've hacked it by editing the page after load ... but can't currently find where those option values are being pulled from. Generations are fast and I seem to be able to make larger images that before. Needs more testing, but seems very positive. |
|
@discordinated did you update the environment? The latest k-diffusion by @Birch-san already has the samplers merged, so it shouldn't be needed to switch to crowsonkb's. |
|
@lstein @CapableWeb some users are interested in testing the samplers and results have been positive so far. Is there something else that should be done before considering merging the changes? Let me know if I can help. |
|
I'm happy to merge this in now, but we need another reviewer. I will add a few candidates. |
|
@victorca25 - Thanks for your work on this, and on behalf of the team, thanks for understanding why its been open for as long as it has been. I know users value these samplers quite a bit, and I am personally excited to get my hands on them. We're in the process of migrating to diffusers (branch is https://github.com/invoke-ai/InvokeAI/tree/dev/diffusers) - In the interest of not moving the goal posts on @keturn more than has been already, could you look into compatibility with diffusers and introduce a PR off of dev/diffusers that would add these samplers into our diffusers work as well? Know it's a bigger ask than us just reviewing existing code and merging in, but we're trying to make sure we can ensure that we'll be able to maintain compatibility for these once we migrate before approving & merging in on our legacy backend. Whether you take that on or not, any insight you can share on compatibility w/ diffusers would be appreciated! |
Sorry for slow reply - hectic days here. Yes I did but to double check I started over. I installed Invoke again the other day to check out 2.2 so I just used 'gh pr checkout 1389' to get this PR branch, then did a 'git pull' for good measure. It was all up to date. Then I updated the env using 'conda env update' and then edited the GUI .js to show the samplers in the webui. All good to that point. When trying to generate using one of the new samplers I had this error: `>> Image generation requested: {'prompt': 'snow covered slope, a microscopic photo, by Matthias Weischer, plasticien, 8k fabric texture details, icebergs, broken glass photo, stock photo', 'iterations': 1, 'steps': 40, 'cfg_scale': 8.5, 'threshold': 0, 'perlin': 0, 'height': 768, 'width': 1024, 'sampler_name': 'k_dpmpp_2_a', 'seed': 718800835, 'progress_images': False, 'progress_latents': True, 'save_intermediates': 5, 'generation_mode': 'txt2img', 'init_mask': '...', 'seamless': False, 'hires_fix': True, 'variation_amount': 0}
Traceback (most recent call last): I then swapped /Users/USERNAME/miniconda3/envs/invokeai/lib/python3.10/site-packages/k_diffusion/sampling.py for https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/sampling.py -- torchsde didn't give an error this time, so must still be installed. Restarted invokeai with --web and it works and generates an image: `>> Image generation requested: {'prompt': 'snow covered slope, a microscopic photo, by Matthias Weischer, plasticien, 8k fabric texture details, icebergs, broken glass photo, stock photo', 'iterations': 1, 'steps': 40, 'cfg_scale': 8.5, 'threshold': 0, 'perlin': 0, 'height': 768, 'width': 1024, 'sampler_name': 'k_dpmpp_2_a', 'seed': 718800835, 'progress_images': False, 'progress_latents': True, 'save_intermediates': 5, 'generation_mode': 'txt2img', 'init_mask': '...', 'seamless': False, 'hires_fix': True, 'variation_amount': 0}
|
|
Hello @hipsterusername, |
|
@discordinated the torchsde dependency was not added by this PR, but by some other changes in the development branch. I've been updating the PR with the changes in development since I opened it, but it is probably an issue introduced by a different change |
|
That makes sense, I've reverted back to Dev and undone the change as I was getting some other issues. Look forward to seeing the ++ samplers in dev / main - they're a great step forward. |
* Fixes inpainting + code cleanup * Disable stage info in Inpainting Tab * Mask Brush Preview now always at 0.5 opacity The new mask is only visible properly at max opacity but at max opacity the brush preview becomes fully opaque blocking the view. So the mask brush preview no remains at 0.5 no matter what the Brush opacity is. * Remove save button from Canvas Controls (cleanup) * Implements invert mask * Changes "Invert Mask" to "Preserve Masked Areas" * Fixes (?) spacebar issues * Patches redux-persist and redux-deep-persist with debounced persists Our app changes redux state very, very often. As our undo/redo history grows, the calls to persist state start to take in the 100ms range, due to a the deep cloning of the history. This causes very noticeable performance lag. The deep cloning is required because we need to blacklist certain items in redux from being persisted (e.g. the app's connection status). Debouncing the whole process of persistence is a simple and effective solution. Unfortunately, `redux-persist` dropped `debounce` between v4 and v5, replacing it with `throttle`. `throttle`, instead of delaying the expensive action until a period of X ms of inactivity, simply ensures the action is executed at least every X ms. Of course, this does not fix our performance issue. The patch is very simple. It adds a `debounce` argument - a number of milliseconds - and debounces `redux-persist`'s `update()` method (provided by `createPersistoid`) by that many ms. Before this, I also tried writing a custom storage adapter for `redux-persist` to debounce the calls to `localStorage.setItem()`. While this worked and was far less invasive, it doesn't actually address the issue. It turns out `setItem()` is a very fast part of the process. We use `redux-deep-persist` to simplify the `redux-persist` configuration, which can get complicated when you need to blacklist or whitelist deeply nested state. There is also a patch here for that library because it uses the same types as `redux-persist`. Unfortunately, the last release of `redux-persist` used a package `flat-stream` which was malicious and has been removed from npm. The latest commits to `redux-persist` (about 1 year ago) do not build; we cannot use the master branch. And between the last release and last commit, the changes have all been breaking. Patching this last release (about 3 years old at this point) directly is far simpler than attempting to fix the upstream library's master branch or figuring out an alternative to the malicious and now non-existent dependency. * Adds debouncing * Fixes AttributeError: 'dict' object has no attribute 'invert_mask' * Updates package.json to use redux-persist patches * Attempts to fix redux-persist debounce patch * Fixes undo/redo * Fixes invert mask * Debounce > 300ms * Limits history to 256 for each of undo and redo * Canvas styling * Hotkeys improvement * Add Metadata To Viewer * Increases CFG Scale max to 200 * Fix gallery width size for Outpainting Also fixes the canvas resizing failing n fast pushes * Fixes disappearing canvas grid lines * Adds staging area * Fixes "use all" not setting variationAmount Now sets to 0 when the image had variations. * Builds fresh bundle * Outpainting tab loads to empty canvas instead of upload * Fixes wonky canvas layer ordering & compositing * Fixes error on inpainting paste back `TypeError: 'float' object cannot be interpreted as an integer` * Hides staging area outline on mouseover prev/next * Fixes inpainting not doing img2img when no mask * Fixes bbox not resizing in outpainting if partially off screen * Fixes crashes during iterative outpaint. Still doesn't work correctly though. * Fix iterative outpainting by restoring original images * Moves image uploading to HTTP - It all seems to work fine - A lot of cleanup is still needed - Logging needs to be added - May need types to be reviewed * Fixes: outpainting temp images show in gallery * WIP refactor to unified canvas * Removes console.log from redux-persist patch * Initial unification of canvas * Removes all references to split inpainting/outpainting canvas * Add patchmatch and infill_method parameter to prompt2image (options are 'patchmatch' or 'tile'). * Fixes app after removing in/out-painting refs * Rebases on dev, updates new env files w/ patchmatch * Organises features/canvas * Fixes bounding box ending up offscreen * Organises features/canvas * Stops unnecessary canvas rescales on gallery state change * Fixes 2px layout shift on toggle canvas lock * Clips lines drawn while canvas locked When drawing with the locked canvas, if a brush stroke gets too close to the edge of the canvas and its stroke would extend past the edge of the canvas, the edge of that stroke will be seen after unlocking the canvas. This could cause a problem if you unlock the canvas and now have a bunch of strokes just outside the init image area, which are far back in undo history and you cannot easily erase. With this change, lines drawn while the canvas is locked get clipped to the initial image bbox, fixing this issue. Additionally, the merge and save to gallery functions have been updated to respect the initial image bbox so they function how you'd expect. * Fixes reset canvas view when locked * Fixes send to buttons * Fixes bounding box not being rounded to 64 * Abandons "inpainting" canvas lock * Fixes save to gallery including empty area, adds download and copy image * Fix Current Image display background going over image bounds * Sets status immediately when clicking Invoke * Adds hotkeys and refactors sharing of konva instances Adds hotkeys to canvas. As part of this change, the access to konva instance objects was refactored: Previously closure'd refs were used to indirectly get access to the konva instances outside of react components. Now, a getter and setter function are used to provide access directly to the konva objects. * Updates hotkeys * Fixes canvas showing spinner on first load Also adds good default canvas scale and positioning when no image is on it * Fixes possible hang on MaskCompositer * Improves behaviour when setting init canvas image/reset view * Resets bounding box coords/dims when no image present * Disables canvas actions which cannot be done during processing * Adds useToastWatcher hook - Dispatch an `addToast` action with standard Chakra toast options object to add a toast to the toastQueue - The hook is called in App.tsx and just useEffect's w/ toastQueue as dependency to create the toasts - So now you can add toasts anywhere you have access to `dispatch`, which includes middleware and thunks - Adds first usage of this for the save image buttons in canvas * Update Hotkey Info Add missing tooltip hotkeys and update the hotkeys modal to reflect the new hotkeys for the Unified Canvas. * Fix theme changer not displaying current theme on page refresh * Fix tab count in hotkeys panel * Unify Brush and Eraser Sizes * Fix staging area display toggle not working * Staging Area delete button is now red So it doesnt feel blended into to the rest of them. * Revert "Fix theme changer not displaying current theme on page refresh" This reverts commit 903edfb. * Add arguments to use SSL to webserver * Integrates #1487 - touch events Need to add: - Pinch zoom - Touch-specific handling (some things aren't quite right) * Refactors upload-related async thunks - Now standard thunks instead of RTK createAsyncThunk() - Adds toasts for all canvas upload-related actions * Reorganises app file structure * Fixes Canvas Auto Save to Gallery * Fixes staging area outline * Adds staging area hotkeys, disables gallery left/right when staging * Fixes Use All Parameters * Fix metadata viewer image url length when viewing intermediate * Fixes intermediate images being tiny in txt2img/img2img * Removes stale code * Improves canvas status text and adds option to toggle debug info * Fixes paste image to upload * Adds model drop-down to site header * Adds theme changer popover * Fix missing key on ThemeChanger map * Fixes stage position changing on zoom * Hotkey Cleanup - Viewer is now Z - Canvas Move tool is V - sync with PS - Removed some unused hotkeys * Fix canvas resizing when both options and gallery are unpinned * Implements thumbnails for gallery - Thumbnails are saved whenever an image is saved, and when gallery requests images from server - Thumbnails saved at original image aspect ratio with width of 128px as WEBP - If the thumbnail property of an image is unavailable for whatever reason, the image's full size URL is used instead * Saves thumbnails to separate thumbnails directory * Thumbnail size = 256px * Fix Lightbox Issues * Disables canvas image saving functions when processing * Fix index error on going past last image in Gallery * WIP - Lightbox Fixes Still need to fix the images not being centered on load when the image res changes * Fixes another similar index error, simplifies logic * Reworks canvas toolbar * Fixes canvas toolbar upload button * Cleans up IAICanvasStatusText * Improves metadata handling, fixes #1450 - Removes model list from metadata - Adds generation's specific model to metadata - Displays full metadata in JSON viewer * Gracefully handles corrupted images; fixes #1486 - App does not crash if corrupted image loaded - Error is displayed in the UI console and CLI output if an image cannot be loaded * Adds hotkey to reset canvas interaction state If the canvas' interaction state (e.g. isMovingBoundingBox, isDrawing, etc) get stuck somehow, user can press Escape to reset the state. * Removes stray console.log() * Fixes bug causing gallery to close on context menu open * Minor bugfixes - When doing long-running canvas image exporting actions, display indeterminate progress bar - Fix staging area image outline not displaying after committing/discarding results * Removes unused imports * Fixes repo root .gitignore ignoring frontend things * Builds fresh bundle * Styling updates * Removes reasonsWhyNotReady The popover doesn't play well with the button being disabled, and I don't think adds any value. * Image gallery resize/style tweaks * Styles buttons for clearing canvas history and mask * First pass on Canvas options panel * Fixes bug where discarding staged images results in loss of history * Adds Save to Gallery button to staging toolbar * Rearrange some canvas toolbar icons Put brush stuff together and canvas movement stuff together * Fix gallery maxwidth on unified canvas * Update Layer hotkey display to UI * Adds option to crop to bounding box on save * Masking option tweaks * Crop to Bounding Box > Save Box Region Only * Adds clear temp folder * Updates mask options popover behavior * Builds fresh bundle * Fix styling on alert modals * Fix input checkbox styling being incorrect on light theme * Styling fixes * Improves gallery resize behaviour * Cap gallery size on canvas tab so it doesnt overflow * Fixes bug when postprocessing image with no metadata * Adds IAIAlertDialog component * Moves Loopback to app settings * Fixes metadata viewer not showing metadata after refresh Also adds Dream-style prompt to metadata * Adds outpainting specific options * Linting * Fixes gallery width on lightbox, fixes gallery button expansion * Builds fresh bundle * Fix Lightbox images of different res not centering * Update feature tooltip text * Highlight mask icon when on mask layer * Fix gallery not resizing correctly on open and close * Add loopback to just img2img. Remove from settings. * Fix to gallery resizing * Removes Advanced checkbox, cleans up options panel for unified canvas * Minor styling fixes to new options panel layout * Styling Updates * Adds infill method * Tab Styling Fixes * memoize outpainting options * Fix unnecessary gallery re-renders * Isolate Cursor Pos debug text on canvas to prevent rerenders * Fixes missing postprocessed image metadata before refresh * Builds fresh bundle * Fix rerenders on model select * Floating panel re-render fix * Simplify fullscreen hotkey selector * Add Training WIP Tab * Adds Training icon * Move full screen hotkey to floating to prevent tab rerenders * Adds single-column gallery layout * Fixes crash on cancel with intermediates enabled, fixes #1416 * Updates npm dependencies * Fixes img2img attempting inpaint when init image has transparency * Fixes missing threshold and perlin parameters in metadata viewer * Renames "Threshold" > "Noise Threshold" * Fixes postprocessing not being disabled when clicking use all * Builds fresh bundle * Adds color picker * Lints & builds fresh bundle * Fixes iterations being disabled when seed random & variations are off * Un-floors cursor position * Changes color picker preview to circles * Fixes variation params not set correctly when recalled * Fixes invoke hotkey not working in input fields * Simplifies Accordion Prep for adding reset buttons for each section * Fixes mask brush preview color * Committing color picker color changes tool to brush * Color picker does not overwrite user-selected alpha * Adds brush color alpha hotkey * Lints * Removes force_outpaint param * Add inpaint size options to inpaint at a larger size than the actual inpaint image, then scale back down for recombination * Bug fix for inpaint size * Adds inpaint size (as scale bounding box) to UI * Adds auto-scaling for inpaint size * Improves scaled bbox display logic * Fixes bug with clear mask and history * Fixes shouldShowStagingImage not resetting to true on commit * Builds fresh bundle * Fixes canvas failing to scale on first run * Builds fresh bundle * Fixes unnecessary canvas scaling * Adds gallery drag and drop to img2img/canvas * Builds fresh bundle * Fix desktop mode being broken with new versions of flaskwebgui * Fixes canvas dimensions not setting on first load * Builds fresh bundle * stop crash on !import_models call on model inside rootdir - addresses bug report #1546 * prevent "!switch state gets confused if model switching fails" - If !switch were to fail on a particular model, then generate got confused and wouldn't try again until you switch to a different working model and back again. - This commit fixes and closes #1547 * Revert "make the docstring more readable and improve the list_models logic" This reverts commit 248068f. * fix model cache path * also set fail-fast to it's default (true) in this way the whole action fails if one job fails this should unblock the runners!!! * fix output path for Archive results * disable checks for python 3.9 * Update-requirements and test-invoke-pip workflow (#1574) * update requirements files * update test-invoke-pip workflow * move requirements-mkdocs.txt to docs folder (#1575) * move requirements-mkdocs.txt to docs folder * update copyright * Fixes outpainting with resized inpaint size * Interactive configuration (#1517) * Update scripts/configure_invokeai.py prevent crash if output exists Co-authored-by: psychedelicious <[email protected]> * implement changes requested by reviews * default to correct root and output directory on Windows systems - Previously the script was relying on the readline buffer editing feature to set up the correct default. But this feature doesn't exist on windows. - This commit detects when user typed return with an empty directory value and replaces with the default directory. * improved readability of directory choices * Update scripts/configure_invokeai.py Co-authored-by: psychedelicious <[email protected]> * better error reporting at startup - If user tries to run the script outside of the repo or runtime directory, a more informative message will appear explaining the problem. Co-authored-by: psychedelicious <[email protected]> * Embedding merging (#1526) * add whole <style token> to vocab for concept library embeddings * add ability to load multiple concept .bin files * make --log_tokenization respect custom tokens * start working on concept downloading system * preliminary support for dynamic loading and merging of multiple embedded models - The embedding_manager is now enhanced with ldm.invoke.concepts_lib, which handles dynamic downloading and caching of embedded models from the Hugging Face concepts library (https://huggingface.co/sd-concepts-library) - Downloading of a embedded model is triggered by the presence of one or more <concept> tags in the prompt. - Once the embedded model is downloaded, its trigger phrase will be loaded into the embedding manager and the prompt's <concept> tag will be replaced with the <trigger_phrase> - The downloaded model stays on disk for fast loading later. - The CLI autocomplete will complete partial <concept> tags for you. Type a '<' and hit tab to get all ~700 concepts. BUGS AND LIMITATIONS: - MODEL NAME VS TRIGGER PHRASE You must use the name of the concept embed model from the SD library, and not the trigger phrase itself. Usually these are the same, but not always. For example, the model named "hoi4-leaders" corresponds to the trigger "<HOI4-Leader>" One reason for this design choice is that there is no apparent constraint on the uniqueness of the trigger phrases and one trigger phrase may map onto multiple models. So we use the model name instead. The second reason is that there is no way I know of to search Hugging Face for models with certain trigger phrases. So we'd have to download all 700 models to index the phrases. The problem this presents is that this may confuse users, who will want to reuse prompts from distributions that use the trigger phrase directly. Usually this will work, but not always. - WON'T WORK ON A FIREWALLED SYSTEM If the host running IAI has no internet connection, it can't download the concept libraries. I will add a script that allows users to preload a list of concept models. - BUG IN PROMPT REPLACEMENT WHEN MODEL NOT FOUND There's a small bug that occurs when the user provides an invalid model name. The <concept> gets replaced with <None> in the prompt. * fix loading .pt embeddings; allow multi-vector embeddings; warn on dupes * simplify replacement logic and remove cuda assumption * download list of concepts from hugging face * remove misleading customization of '*' placeholder the existing code as-is did not do anything; unclear what it was supposed to do. the obvious alternative -- setting using 'placeholder_strings' instead of 'placeholder_tokens' to match model.params.personalization_config.params.placeholder_strings -- caused a crash. i think this is because the passed string also needed to be handed over on init of the PersonalizedBase as the 'placeholder_token' argument. this is weird config dict magic and i don't want to touch it. put a breakpoint in personalzied.py line 116 (top of PersonalizedBase.__init__) if you want to have a crack at it yourself. * address all the issues raised by damian0815 in review of PR #1526 * actually resize the token_embeddings * multiple improvements to the concept loader based on code reviews 1. Activated the --embedding_directory option (alias --embedding_path) to load a single embedding or an entire directory of embeddings at startup time. 2. Can turn off automatic loading of embeddings using --no-embeddings. 3. Embedding checkpoints are scanned with the pickle scanner. 4. More informative error messages when a concept can't be loaded due either to a 404 not found error or a network error. * autocomplete terms end with ">" now * fix startup error and network unreachable 1. If the .invokeai file does not contain the --root and --outdir options, invoke.py will now fix it. 2. Catch and handle network problems when downloading hugging face textual inversion concepts. * fix misformatted error string Co-authored-by: Damian Stewart <[email protected]> * model_cache.py: fix list_models Signed-off-by: devops117 <[email protected]> * add statement of values (#1584) * this adds the Statement of Values Google doc source = https://docs.google.com/document/d/1-PrUKDJcxy8OyNGc8CyiHhv2VgLvjt7LRGlEpbg1nmQ/edit?usp=sharing * Fix heading * Update InvokeAI_Statement_of_Values.md * Update InvokeAI_Statement_of_Values.md * Update InvokeAI_Statement_of_Values.md * Update InvokeAI_Statement_of_Values.md * Update InvokeAI_Statement_of_Values.md * add keturn and mauwii to the team member list * Fix punctuation * this adds the Statement of Values Google doc source = https://docs.google.com/document/d/1-PrUKDJcxy8OyNGc8CyiHhv2VgLvjt7LRGlEpbg1nmQ/edit?usp=sharing * add keturn and mauwii to the team member list * fix formating - make sub bullets use * (decide to all use - or *) - indent sub bullets Sorry, first only looked at the code version and found this only after looking at the markdown rendered version * use multiparagraph numbered sections * Break up Statement Of Values as per comments on #1584 * remove duplicated word, reduce vagueness it's important not to overstate how many artists we are consulting. * fix typo (sorry blessedcoolant) Co-authored-by: mauwii <[email protected]> Co-authored-by: damian <[email protected]> * update dockerfile (#1551) * update dockerfile * remove not existing file from .dockerignore * remove bloat and unecesary step also use --no-cache-dir for pip install image is now close to 2GB * make Dockerfile a variable * set base image to `ubuntu:22.10` * add build-essential * link outputs folder for persistence * update tag variable * update docs * fix not customizeable build args, add reqs output * !model_import autocompletes in ROOTDIR * Adds psychedelicious to statement of values signature (#1602) * add a --no-patchmatch option to disable patchmatch loading (#1598) This feature was added to prevent the CI Macintosh tests from erroring out when patchmatch is unable to retrieve its shared library from github assets. * Fix #1599 by relaxing the `match_trigger` regex (#1601) * Fix #1599 by relaxing the `match_trigger` regex Also simplify logic and reduce duplication. * restrict trigger regex again (but not so far) * make concepts library work with Web UI This PR makes it possible to include a Hugging Face concepts library <style-or-subject-trigger> in the WebUI prompt. The metadata seems to be correctly handled. * documentation enhancements (#1603) - Add documentation for the Hugging Face concepts library and TI embedding. - Fixup index.md to point to each of the feature documentation files, including ones that are pending. * tweak setup and environment files for linux & pypatchmatch (#1580) * tweak setup and environment files for linux & pypatchmatch - Downgrade python requirements to 3.9 because 3.10 is not supported on Ubuntu 20.04 LTS (widely-used distro) - Use our github pypatchmatch 0.1.3 in order to install Makefile where it needs to be. - Restored "-e ." as the last install step on pip installs. Hopefully this will not trigger the high-CPU hang we've previously experienced. * keep windows on basicsr 1.4.1 * keep windows on basicsr 1.4.1 * bump pypatchmatch requirement to 0.1.4 - This brings in a version of pypatchmatch that will gracefully handle internet connection not available at startup time. - Also refactors and simplifies the handling of gfpgan's basicsr requirement across various platforms. * revert to older version of list_models() (#1611) This restores the correct behavior of list_models() and quenches the bug of list_models() returning a single model entry named "name". I have not investigated what was wrong with the new version, but I think it may have to do with changes to the behavior in dict.update() * Fixes for #1604 (#1605) * Converts ESRGAN image input to RGB - Also adds typing for image input. - Partially resolves #1604 * ensure there are unmasked pixels before color matching Co-authored-by: Kyle Schouviller <[email protected]> * update index.md (#1609) - comment out non existing link - fix indention - add seperator between feature categories * Debloat-docker (#1612) * debloat Dockerfile - less options more but more userfriendly - better Entrypoint to simulate CLI usage - without command the container still starts the web-host * debloat build.sh * better syntax in run.sh * update Docker docs - fix description of VOLUMENAME - update run script example to reflect new entrypoint * Test installer (#1618) * test linux install * try removing http from parsed requirements * pip install confirmed working on linux * ready for linux testing - rebuilt py3.10-linux-x86_64-cuda-reqs.txt to include pypatchmatch dependency. - point install.sh and install.bat to test-installer branch. * Updates MPS reqs * detect broken readline history files * fix download.pytorch.org URL * Test installer (Win 11) (#1620) Co-authored-by: Cyrus Chan <[email protected]> * Test installer (MacOS 13.0.1 w/ torch==1.12.0) (#1621) * Test installer (Win 11) * Test installer (MacOS 13.0.1 w/ torch==1.12.0) Co-authored-by: Cyrus Chan <[email protected]> * change sourceball to development for testing * Test installer (MacOS 13.0.1 w/ torch==1.12.1 & torchvision==1.13.1) (#1622) * Test installer (Win 11) * Test installer (MacOS 13.0.1 w/ torch==1.12.0) * Test installer (MacOS 13.0.1 w/ torch==1.12.1 & torchvision==1.13.1) Co-authored-by: Cyrus Chan <[email protected]> Co-authored-by: psychedelicious <[email protected]> Co-authored-by: Cyrus Chan <[email protected]> Co-authored-by: Cyrus Chan <[email protected]> * 2.2 Doc Updates (#1589) * Unified Canvas Docs & Assets Unified Canvas draft Advanced Tools Updates Doc Updates (lstein feedback) * copy edits to Unified Canvas docs - consistent capitalisation and feature naming - more intimate address (replace "the user" with "you") for improved User Engagement(tm) - grammatical massaging and *poesie* Co-authored-by: Lincoln Stein <[email protected]> Co-authored-by: damian <[email protected]> * include a step after config to `cat ~/.invokeai` (#1629) * disable patchmatch in CI actions (#1626) * disable patchmatch in CI actions * fix indention * replace tab with spaces Co-authored-by: Matthias Wild <[email protected]> Co-authored-by: mauwii <[email protected]> * Fix installer script for macOS. (#1630) * refer to the platform as 'osx' instead of 'mac', otherwise the composed URL to micromamba is wrong. * move the `-O` option to `tar` to be grouped with the other tar flags to avoid the `-O` being interpreted as something to unarchive. * Removes symlinked environment.yaml (#1631) Was unintentionally added in #1621 * Fix inpainting with iterations (#1635) * fix error when inpainting using runwayml inpainting model (#1634) - error was "Omnibus object has no attribute pil_image" - closes #1596 * add k_dpmpp_2_a and k_dpmpp_2 solvers options (#1389) * add k_dpmpp_2_a and k_dpmpp_2 solvers options * update frontend Co-authored-by: Victor <[email protected]> Co-authored-by: Lincoln Stein <[email protected]> * add .editorconfig (#1636) * Web UI 2.2 bugfixes (#1572) * Fixes bug preventing multiple images from being generated * Fixes valid seam strength value range * Update Delete Alert Text Indicates to the user that images are not permanently deleted. * Fixes left/right arrows not working on gallery * Fixes initial image on load erroneously set to a user uploaded image Should be a result gallery image. * Lightbox Fixes - Lightbox is now a button in the current image buttons - Lightbox is also now available in the gallery context menu - Lightbox zoom issues fixed - Lightbox has a fade in animation. * Fix image display wrapper in current preview not overflow bounds * Revert "Fix image display wrapper in current preview not overflow bounds" This reverts commit 5511c82. * Change Staging Area discard icon from Bin to X * Expose Snap Threshold and Move Snap Settings to BBox Panel * Changes img2img strength default to 0.75 * Fixes drawing triggering when mouse enters canvas w/ button down When we only supported inpainting and no zoom, this was useful. It allowed the cursor to leave the canvas (which was easy to do given the limited canvas dimensions) and without losing the "I am drawing" state. With a zoomable canvas this is no longer as useful. Additionally, we have more popovers and tools (like the color pickers) which result in unexpected brush strokes. This fixes that issue. * Revert "Expose Snap Threshold and Move Snap Settings to BBox Panel" We will handle this a bit differently - by allowing the grid origin to be moved. I will dig in at some point. This reverts commit 33c92ec. * Adds Limit Strokes to Box * Adds fill bounding box button * Adds erase bounding box button * Changes Staging area discard icon to match others * Fixes right click breaking move tool * Fixes brush preview visibility issue with "darken outside box" * Fixes history bugs with addFillRect, addEraseRect, and other actions * Adds missing `key` * Fixes postprocessing being applied to canvas generations * Fixes bbox not getting scaled in various situations * Fixes staging area show image toggle not resetting on accept/discard * Locks down canvas while generating/staging * Fixes move tool breaking when canvas loses focus during move/transform * Hides cursor when restrict strokes is on and mouse outside bbox * Lints * Builds fresh bundle * Fix overlapping hotkey for Fill Bounding Box * Build Fresh Bundle * Fixes bug with mask and bbox overlay * Builds fresh bundle Co-authored-by: blessedcoolant <[email protected]> Co-authored-by: Lincoln Stein <[email protected]> * disable NSFW checker loading during the CI tests (#1641) * disable NSFW checker loading during the CI tests The NSFW filter apparently causes invoke.py to crash during CI testing, possibly due to out of memory errors. This workaround disables NSFW model loading. * doc change * fix formatting errors in yml files * Configure the NSFW checker at install time with default on (#1624) * configure the NSFW checker at install time with default on 1. Changes the --safety_checker argument to --nsfw_checker and --no-nsfw_checker. The original argument is recognized for backward compatibility. 2. The configure script asks users whether to enable the checker (default yes). Also offers users ability to select default sampler and number of generation steps. 3.Enables the pasting of the caution icon on blurred images when InvokeAI is installed into the package directory. 4. Adds documentation for the NSFW checker, including caveats about accuracy, memory requirements, and intermediate image dispaly. * use better fitting icon * NSFW defaults false for testing * set default back to nsfw active Co-authored-by: Matthias Wild <[email protected]> Co-authored-by: mauwii <[email protected]> Signed-off-by: devops117 <[email protected]> Co-authored-by: psychedelicious <[email protected]> Co-authored-by: blessedcoolant <[email protected]> Co-authored-by: Kyle Schouviller <[email protected]> Co-authored-by: javl <[email protected]> Co-authored-by: Kent Keirsey <[email protected]> Co-authored-by: mauwii <[email protected]> Co-authored-by: Matthias Wild <[email protected]> Co-authored-by: Damian Stewart <[email protected]> Co-authored-by: DevOps117 <[email protected]> Co-authored-by: damian <[email protected]> Co-authored-by: Damian Stewart <[email protected]> Co-authored-by: Cyrus Chan <[email protected]> Co-authored-by: Cyrus Chan <[email protected]> Co-authored-by: Andre LaBranche <[email protected]> Co-authored-by: victorca25 <[email protected]> Co-authored-by: Victor <[email protected]>
|
After a series of inpainting escapades this evening (in this case swapping a face for (This is likely a different issue, one that I've experienced before after a lengthy session without restarting the front/back end; I'll try and ticket that with something concrete afterward.) But while screwing around, shotgun-debugging, I went back to txt2img to just generate any image, and while changing the sampler, I noticed So I went to give it a go, and the backend threw this: >> Image generation requested: {'prompt': 'kate mulgrew', 'iterations': 1, 'steps': 32, 'cfg_scale': 7, 'threshold': 0, 'perlin': 0, 'height': 512, 'width': 512, 'sampler_name': 'k_dpmpp_2_a', 'seed': 3590536378, 'progress_images': False, 'progress_latents': True, 'save_intermediates': 5, 'generation_mode': 'txt2img', 'init_mask': '...', 'seamless': False, 'hires_fix': False, 'variation_amount': 0}
ESRGAN parameters: False
Facetool parameters: False
{'prompt': 'kate mulgrew', 'iterations': 1, 'steps': 32, 'cfg_scale': 7, 'threshold': 0, 'perlin': 0, 'height': 512, 'width': 512, 'sampler_name': 'k_dpmpp_2_a', 'seed': 3590536378, 'progress_images': False, 'progress_latents': True, 'save_intermediates': 5, 'generation_mode': 'txt2img', 'init_mask': '', 'seamless': False, 'hires_fix': False, 'variation_amount': 0}
Generating: 0%| | 0/1 [00:00<?, ?it/s]>> Ksampler using model noise schedule (steps >= 30)
>> Sampling with k_dpmpp_2s_ancestral starting at step 0 of 32 (32 new sampling steps)
Generating: 0%| | 0/1 [00:00<?, ?it/s]
'sample_dpmpp_2s_ancestral'
Traceback (most recent call last):
File "/home/fortyseven/opt/ai/invoke-ai/backend/invoke_ai_web_server.py", line 1116, in generate_images
self.generate.prompt2image(
File "/home/fortyseven/opt/ai/invoke-ai/ldm/generate.py", line 486, in prompt2image
results = generator.generate(
File "/home/fortyseven/opt/ai/invoke-ai/ldm/invoke/generator/base.py", line 93, in generate
image = make_image(x_T)
File "/home/fortyseven/opt/ai/invoke-ai/venv/lib/python3.10/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/fortyseven/opt/ai/invoke-ai/ldm/invoke/generator/txt2img.py", line 39, in make_image
samples, _ = sampler.sample(
File "/home/fortyseven/opt/ai/invoke-ai/venv/lib/python3.10/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/fortyseven/opt/ai/invoke-ai/ldm/models/diffusion/ksampler.py", line 214, in sample
K.sampling.__dict__[f'sample_{self.schedule}'](
KeyError: 'sample_dpmpp_2s_ancestral' |
Following up from #1383, these are the changes needed in case anyone wants to test the new DPM++ solvers (crowsonkb/k-diffusion@2d2240b), but based on the development branch.
Copying the same notes as before for reference:
On Mac M1 k_dpmpp_2 results in black images, the ancestral k_dpmpp_2_a works, but I think it suffers from the same as #1350 , so it might work better elsewhere.
To use, k-diffusion (src/k-diffusion/k_diffusion/sampling.py) has to be updated with the sample_dpmpp_2s_ancestral() and sample_dpmpp_2m() functions. Might be interesting to evaluate these new versions. More info: crowsonkb/k-diffusion#40