diff --git a/README.md b/README.md index 8d108733ea..1b8bbe6758 100644 --- a/README.md +++ b/README.md @@ -1,17 +1,39 @@ # Stable Diffusion Dream Script This is a fork of CompVis/stable-diffusion, the wonderful open source -text-to-image generator. The original has been improved in several ways: +text-to-image generator. This fork supports: + +1. An interactive command-line interface that accepts the same prompt +and switches as the Discord bot. + +2. Support for img2img in which you provide a seed image to build on +top of. + +3. A basic Web interface that allows you to run a local web server for +generating images in your browser. + +4. Upscaling and face fixing using the optional ESRGAN and GFPGAN +packages. + +5. Weighted subprompts for prompt tuning. + +6. Textual inversion for customization of the prompt language and images. + +7. ...and more! + +This fork is rapidly evolving, so use the Issues panel to report bugs +and make feature requests, and check back periodically for +improvements and bug fixes. ## Interactive command-line interface similar to the Discord bot -The *dream.py* script, located in scripts/dream.py, +The _dream.py_ script, located in scripts/dream.py, provides an interactive interface to image generation similar to the "dream mothership" bot that Stable AI provided on its Discord server. Unlike the txt2img.py and img2img.py scripts provided in the original CompViz/stable-diffusion source code repository, the time-consuming initialization of the AI model -initialization only happens once. After that image generation +initialization only happens once. After that image generation from the command-line interface is very fast. The script uses the readline library to allow for in-line editing, @@ -25,7 +47,7 @@ The script is confirmed to work on Linux and Windows systems. It should work on MacOSX as well, but this is not confirmed. Note that this script runs from the command-line (CMD or Terminal window), and does not have a GUI. -~~~~ +``` (ldm) ~/stable-diffusion$ python3 ./scripts/dream.py * Initializing, be patient... Loading model from models/ldm/text2img-large/model.ckpt @@ -47,13 +69,13 @@ dream> q 00009.png: "ashley judd riding a camel" -s150 -S 416354203 00010.png: "ashley judd riding a camel" -s150 -S 1362479620 00011.png: "there's a fly in my soup" -n6 -g -S 2685670268 -~~~~ +``` The dream> prompt's arguments are pretty much identical to those used in the Discord bot, except you don't need to type "!dream" (it doesn't hurt if you do). A significant change is that creation of individual images is now the default unless --grid (-g) is given. For backward -compatibility, the -i switch is recognized. For command-line help +compatibility, the -i switch is recognized. For command-line help type -h (or --help) at the dream> prompt. The script itself also recognizes a series of command-line switches @@ -65,12 +87,12 @@ image outputs and the location of the model weight files. This script also provides an img2img feature that lets you seed your creations with a drawing or photo. This is a really cool feature that tells stable diffusion to build the prompt on top of the image you provide, preserving -the original's basic shape and layout. To use it, provide the --init_img +the original's basic shape and layout. To use it, provide the --init_img option as shown here: -~~~~ +``` dream> "waterfall and rainbow" --init_img=./init-images/crude_drawing.png --strength=0.5 -s100 -n4 -~~~~ +``` The --init_img (-I) option gives the path to the seed picture. --strength (-f) controls how much the original will be modified, ranging from 0.0 (keep the original intact), to 1.0 (ignore the original @@ -80,92 +102,131 @@ You may also pass a -v option to generate count variants on the original passing the first generated image back into img2img the requested number of times. It generates interesting variants. -## GFPGAN Support +## GFPGAN and Real-ESRGAN Support -This script also provides the ability to invoke GFPGAN after image -generation. Doing so will enhance faces and optionally upscale the -image to a higher resolution. +The script also provides the ability to do face restoration and +upscaling with the help of GFPGAN and Real-ESRGAN respectively. -To use the ability, clone the [GFPGAN -repository](https://github.com/TencentARC/GFPGAN) and follow their +To use the ability, clone the **[GFPGAN +repository](https://github.com/TencentARC/GFPGAN)** and follow their installation instructions. By default, we expect GFPGAN to be -installed in a 'GFPGAN' sibling directory. Be sure that the "ldm" +installed in a 'GFPGAN' sibling directory. Be sure that the `"ldm"` conda environment is active as you install GFPGAN. -You may also want to install Real-ESRGAN, if you want to enhance -non-face regions in the image, by installing the pip Real-ESRGAN -package. +You can use the `--gfpgan_dir` argument with `dream.py` to set a +custom path to your GFPGAN directory. _There are other GFPGAN related +boot arguments if you wish to customize further._ + +You can install **Real-ESRGAN** by typing the following command. ``` pip install realesrgan - ``` +**Preloading Models** + Users whose GPU machines are isolated from the Internet (e.g. on a University cluster) should be aware that the first time you run -dream.py with GFPGAN turned on, it will try to download model files -from the Internet. To rectify this, you may run `python3 -scripts/preload_models.pl` after you have installed GFPGAN and all its -dependencies. +dream.py with GFPGAN and Real-ESRGAN turned on, it will try to +download model files from the Internet. To rectify this, you may run +`python3 scripts/preload_models.py` after you have installed GFPGAN +and all its dependencies. -Now, you can run this script by adding the **--gfpgan** option. Any -issues with GFPGAN will be reported on initialization. +**Usage** -~~~~ -(ldm) ~/stable-diffusion$ python3 ./scripts/dream.py --gfpgan -* Initializing, be patient... -(...more initialization messages...) -* --gfpgan was specified, loading gfpgan... -(...even more initialization messages...) -* Initialization done! Awaiting your command... -~~~~ +You will now have access to two new prompt arguments. -When generating prompts, add a -G or --gfpgan_strenth option to -control the strength of the GFPGAN enhancement. 0.0 is no -enhancement, 1.0 is maximum enhancement. +**Upscaling** -So for instance, to apply the maximum strength: -~~~~ -dream> a man wearing a pineapple hat -G 1 -~~~~ +`-U : ` + +The upscaling prompt argument takes two values. The first value is a +scaling factor and should be set to either `2` or `4` only. This will +either scale the image 2x or 4x respectively using different models. + +You can set the scaling stength between `0` and `1.0` to control +intensity of the of the scaling. This is handy because AI upscalers +generally tend to smooth out texture details. If you wish to retain +some of those for natural looking results, we recommend using values +between `0.5 to 0.8`. + +If you do not explicitly specify an upscaling_strength, it will +default to 0.75. + +**Face Restoration** + +`-G : ` + +This prompt argument controls the strength of the face restoration +that is being applied. Similar to upscaling, values between `0.5 to +0.8` are recommended. + +You can use either one or both without any conflicts. In cases where +you use both, the image will be first upscaled and then the face +restoration process will be executed to ensure you get the highest +quality facial features. + +`--save_orig` + +When you use either `-U` or `-G`, the final result you get is upscaled +or face modified. If you want to save the original Stable Diffusion +generation, you can use the `-save_orig` prompt argument to save the +original unaffected version too. + +**Example Usage** + +``` +dream > superman dancing with a panda bear -U 2 0.6 -G 0.4 +``` This also works with img2img: -~~~ -dream> a man wearing a pineapple hat -I path/to/your/file.png -G 1 -~~~ -That's it! +``` +dream> a man wearing a pineapple hat -I path/to/your/file.png -U 2 0.5 -G 0.6 +``` -There's also a bunch of options to control GFPGAN settings when -starting the script for different configs that you can read about in -the help text. This will let you control where GFPGAN is installed, if -upsampling is enabled, the upsampler to use and the model path. +**Note** -By default, images will be upscaled by 2-fold, meaning that the old -Stable Diffusion default size of 512x512 will now be a glorious -detailed 1024x1024. The extent of upscaling is set when you run the -script, and can't be changed while it's running. However, at any time -you may specify **-G0** to turn off upscaling and facial enhancement -for that image or set of images. +GFPGAN and Real-ESRGAN are both memory intensive. In order to avoid +crashes and memory overloads during the Stable Diffusion process, +these effects are applied after Stable Diffusion has completed its +work. -Note that loading GFPGAN consumes additional GPU memory, and will add -a few seconds to image generation. However, if can afford a 3090s with -24Gi, the results are well worth it. +In single image generations, you will see the output right away but +when you are using multiple iterations, the images will first be +generated and then upscaled and face restored after that process is +complete. While the image generation is taking place, you will still +be able to preview the base images. + +If you wish to stop during the image generation but want to upscale or +face restore a particular generated image, pass it again with the same +prompt and generated seed along with the `-U` and `-G` prompt +arguments to perform those actions. + +## Google Colab + +Stable Diffusion AI Notebook: Open In Colab
+Open and follow instructions to use an isolated environment running Dream.
+ +Output example: +![Colab Notebook](static/colab_notebook.png) ## Barebones Web Server As of version 1.10, this distribution comes with a bare bones web -server (see screenshot). To use it, run the command: +server (see screenshot). To use it, run the *dream.py* script by +adding the **--web** option. -~~~~ -(ldm) ~/stable-diffusion$ python3 scripts/dream_web.py -~~~~ +``` +(ldm) ~/stable-diffusion$ python3 scripts/dream_web.py --web +``` You can then connect to the server by pointing your web browser at http://localhost:9090, or to the network name or IP address of the server. Kudos to [Tesseract Cat](https://github.com/TesseractCat) for -contributing this code. +contributing this code, and to [dagf2101](https://github.com/dagf2101) +for refining it. ![Dream Web Server](static/dream_web_server.png) @@ -176,17 +237,23 @@ you want to run, one line per prompt. The text file must be composed with a text editor (e.g. Notepad) and not a word processor. Each line should look like what you would type at the dream> prompt: -~~~~ +``` a beautiful sunny day in the park, children playing -n4 -C10 stormy weather on a mountain top, goats grazing -s100 innovative packaging for a squid's dinner -S137038382 -~~~~ +``` Then pass this file's name to dream.py when you invoke it: -~~~~ -(ldm) ~/stable-diffusion$ python3 scripts/dream.py --from_file="path/to/prompts.txt" -~~~~ +``` +(ldm) ~/stable-diffusion$ python3 scripts/dream.py --from_file "path/to/prompts.txt" +``` + +You may read a series of prompts from standard input by providing a filename of "-": + +``` +(ldm) ~/stable-diffusion$ echo "a beautiful day" | python3 scripts/dream.py --from_file - +``` ## Shortcut for reusing seeds from the previous command @@ -202,7 +269,7 @@ Here's an example of using this to do a quick refinement. It also illustrates using the new **-G** switch to turn on upscaling and face enhancement (see previous section): -~~~~ +``` dream> a cute child playing hopscotch -G0.5 [...] outputs/img-samples/000039.3498014304.png: "a cute child playing hopscotch" -s50 -b1 -W512 -H512 -C7.5 -mk_lms -S3498014304 @@ -212,9 +279,7 @@ dream> a cute child playing hopscotch -G1.0 -s100 -S -1 reusing previous seed 3498014304 [...] outputs/img-samples/000040.3498014304.png: "a cute child playing hopscotch" -G1.0 -s100 -b1 -W512 -H512 -C7.5 -mk_lms -S3498014304 -~~~~ - - +``` ## Weighted Prompts @@ -222,9 +287,9 @@ You may weight different sections of the prompt to tell the sampler to attach di priority to them, by adding :(number) to the end of the section you wish to up- or downweight. For example consider this prompt: -~~~~ +``` tabby cat:0.25 white duck:0.75 hybrid -~~~~ +``` This will tell the sampler to invest 25% of its effort on the tabby cat aspect of the image and 75% on the white duck aspect @@ -239,7 +304,7 @@ and introducing a new vocabulary to the fixed model. To train, prepare a folder that contains images sized at 512x512 and execute the following: -~~~~ +``` # As the default backend is not available on Windows, if you're using that platform, execute SET PL_TORCH_DISTRIBUTED_BACKEND=gloo (ldm) ~/stable-diffusion$ python3 ./main.py --base ./configs/stable-diffusion/v1-finetune.yaml \ -t \ @@ -248,14 +313,14 @@ To train, prepare a folder that contains images sized at 512x512 and execute the --gpus 0, \ --data_root D:/textual-inversion/my_cat \ --init_word 'cat' -~~~~ +``` During the training process, files will be created in /logs/[project][time][project]/ where you can see the process. -conditioning* contains the training prompts +conditioning\* contains the training prompts inputs, reconstruction the input images for the training epoch -samples, samples scaled for a sample of the prompt and one with the init word provided +samples, samples scaled for a sample of the prompt and one with the init word provided On a RTX3090, the process for SD will take ~1h @1.6 iterations/sec. @@ -269,28 +334,29 @@ heat death of the universe, when you find a low loss epoch or around Once the model is trained, specify the trained .pt file when starting dream using -~~~~ +``` (ldm) ~/stable-diffusion$ python3 ./scripts/dream.py --embedding_path /path/to/embedding.pt --full_precision -~~~~ +``` Then, to utilize your subject at the dream prompt -~~~ +``` dream> "a photo of *" -~~~ +``` this also works with image2image -~~~~ + +``` dream> "waterfall and rainbow in the style of *" --init_img=./init-images/crude_drawing.png --strength=0.5 -s100 -n4 -~~~~ +``` It's also possible to train multiple tokens (modify the placeholder string in configs/stable-diffusion/v1-finetune.yaml) and combine LDM checkpoints using: -~~~~ +``` (ldm) ~/stable-diffusion$ python3 ./scripts/merge_embeddings.py \ --manager_ckpts /path/to/first/embedding.pt /path/to/second/embedding.pt [...] \ --output_path /path/to/output/embedding.pt -~~~~ +``` Credit goes to @rinongal and the repository located at https://github.com/rinongal/textual_inversion Please see the @@ -298,80 +364,104 @@ repository and associated paper for details and limitations. ## Changes - * v1.11 (26 August 2022) - * NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module. (kudos to [Oceanswave](https://github.com/Oceanswave) - * You now can specify a seed of -1 to use the previous image's seed, -2 to use the seed for the image generated before that, etc. - Seed memory only extends back to the previous command, but will work on all images generated with the -n# switch. - * Variant generation support temporarily disabled pending more general solution. - * Created a feature branch named **yunsaki-morphing-dream** which adds experimental support for - iteratively modifying the prompt and its parameters. Please see[ Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86) - for a synopsis of how this works. Note that when this feature is eventually added to the main branch, it will may be modified - significantly. - -* v1.10 (25 August 2022) - * A barebones but fully functional interactive web server for online generation of txt2img and img2img. - -* v1.09 (24 August 2022) - * A new -v option allows you to generate multiple variants of an initial image - in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave). [ - See this discussion in the PR for examples and details on use](https://github.com/lstein/stable-diffusion/pull/71#issuecomment-1226700810)) - * Added ability to personalize text to image generation (kudos to [Oceanswave](https://github.com/Oceanswave) and [nicolai256](https://github.com/nicolai256)) - * Enabled all of the samplers from k_diffusion - -* v1.08 (24 August 2022) - * Escape single quotes on the dream> command before trying to parse. This avoids - parse errors. - * Removed instruction to get Python3.8 as first step in Windows install. - Anaconda3 does it for you. - * Added bounds checks for numeric arguments that could cause crashes. - * Cleaned up the copyright and license agreement files. +- v1.13 (in process) + - Supports a Google Colab notebook for a standalone server running on Google hardware [Arturo Mendivil](https://github.com/artmen1516) + - WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling [Kevin Gibbons](https://github.com/bakkot) + - WebUI supports incremental display of in-progress images during generation [Kevin Gibbons](https://github.com/bakkot) + - Output directory can be specified on the dream> command line. + - The grid was displaying duplicated images when not enough images to fill the final row [Muhammad Usama](https://github.com/SMUsamaShah) + - Can specify --grid on dream.py command line as the default. + - Miscellaneous internal bug and stability fixes. -* v1.07 (23 August 2022) - * Image filenames will now never fill gaps in the sequence, but will be assigned the - next higher name in the chosen directory. This ensures that the alphabetic and chronological - sort orders are the same. +- v1.12 (28 August 2022) -* v1.06 (23 August 2022) - * Added weighted prompt support contributed by [xraxra](https://github.com/xraxra) - * Example of using weighted prompts to tweak a demonic figure contributed by [bmaltais](https://github.com/bmaltais) + - Improved file handling, including ability to read prompts from standard input. + (kudos to [Yunsaki](https://github.com/yunsaki) + - The web server is now integrated with the dream.py script. Invoke by adding --web to + the dream.py command arguments. + - Face restoration and upscaling via GFPGAN and Real-ESGAN are now automatically + enabled if the GFPGAN directory is located as a sibling to Stable Diffusion. + VRAM requirements are modestly reduced. Thanks to both [Blessedcoolant](https://github.com/blessedcoolant) and + [Oceanswave](https://github.com/oceanswave) for their work on this. + - You can now swap samplers on the dream> command line. [Blessedcoolant](https://github.com/blessedcoolant) -* v1.05 (22 August 2022 - after the drop) - * Filenames now use the following formats: - 000010.95183149.png -- Two files produced by the same command (e.g. -n2), - 000010.26742632.png -- distinguished by a different seed. +- v1.11 (26 August 2022) + - NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module. (kudos to [Oceanswave](https://github.com/Oceanswave) + - You now can specify a seed of -1 to use the previous image's seed, -2 to use the seed for the image generated before that, etc. + Seed memory only extends back to the previous command, but will work on all images generated with the -n# switch. + - Variant generation support temporarily disabled pending more general solution. + - Created a feature branch named **yunsaki-morphing-dream** which adds experimental support for + iteratively modifying the prompt and its parameters. Please see[ Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86) + for a synopsis of how this works. Note that when this feature is eventually added to the main branch, it will may be modified + significantly. +- v1.10 (25 August 2022) + - A barebones but fully functional interactive web server for online generation of txt2img and img2img. +- v1.09 (24 August 2022) + - A new -v option allows you to generate multiple variants of an initial image + in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave). [ + See this discussion in the PR for examples and details on use](https://github.com/lstein/stable-diffusion/pull/71#issuecomment-1226700810)) + - Added ability to personalize text to image generation (kudos to [Oceanswave](https://github.com/Oceanswave) and [nicolai256](https://github.com/nicolai256)) + - Enabled all of the samplers from k_diffusion +- v1.08 (24 August 2022) - 000011.455191342.01.png -- Two files produced by the same command using - 000011.455191342.02.png -- a batch size>1 (e.g. -b2). They have the same seed. + - Escape single quotes on the dream> command before trying to parse. This avoids + parse errors. + - Removed instruction to get Python3.8 as first step in Windows install. + Anaconda3 does it for you. + - Added bounds checks for numeric arguments that could cause crashes. + - Cleaned up the copyright and license agreement files. - 000011.4160627868.grid#1-4.png -- a grid of four images (-g); the whole grid can - be regenerated with the indicated key +- v1.07 (23 August 2022) - * It should no longer be possible for one image to overwrite another - * You can use the "cd" and "pwd" commands at the dream> prompt to set and retrieve - the path of the output directory. - -* v1.04 (22 August 2022 - after the drop) - * Updated README to reflect installation of the released weights. - * Suppressed very noisy and inconsequential warning when loading the frozen CLIP - tokenizer. + - Image filenames will now never fill gaps in the sequence, but will be assigned the + next higher name in the chosen directory. This ensures that the alphabetic and chronological + sort orders are the same. -* v1.03 (22 August 2022) - * The original txt2img and img2img scripts from the CompViz repository have been moved into - a subfolder named "orig_scripts", to reduce confusion. - -* v1.02 (21 August 2022) - * A copy of the prompt and all of its switches and options is now stored in the corresponding +- v1.06 (23 August 2022) + + - Added weighted prompt support contributed by [xraxra](https://github.com/xraxra) + - Example of using weighted prompts to tweak a demonic figure contributed by [bmaltais](https://github.com/bmaltais) + +- v1.05 (22 August 2022 - after the drop) + + - Filenames now use the following formats: + 000010.95183149.png -- Two files produced by the same command (e.g. -n2), + 000010.26742632.png -- distinguished by a different seed. + + 000011.455191342.01.png -- Two files produced by the same command using + 000011.455191342.02.png -- a batch size>1 (e.g. -b2). They have the same seed. + + 000011.4160627868.grid#1-4.png -- a grid of four images (-g); the whole grid can + be regenerated with the indicated key + + - It should no longer be possible for one image to overwrite another + - You can use the "cd" and "pwd" commands at the dream> prompt to set and retrieve + the path of the output directory. + +- v1.04 (22 August 2022 - after the drop) + + - Updated README to reflect installation of the released weights. + - Suppressed very noisy and inconsequential warning when loading the frozen CLIP + tokenizer. + +- v1.03 (22 August 2022) + + - The original txt2img and img2img scripts from the CompViz repository have been moved into + a subfolder named "orig_scripts", to reduce confusion. + +- v1.02 (21 August 2022) + + - A copy of the prompt and all of its switches and options is now stored in the corresponding image in a tEXt metadata field named "Dream". You can read the prompt using scripts/images2prompt.py, or an image editor that allows you to explore the full metadata. - **Please run "conda env update -f environment.yaml" to load the k_lms dependencies!!** + **Please run "conda env update -f environment.yaml" to load the k_lms dependencies!!** -* v1.01 (21 August 2022) - * added k_lms sampling. - **Please run "conda env update -f environment.yaml" to load the k_lms dependencies!!** - * use half precision arithmetic by default, resulting in faster execution and lower memory requirements +- v1.01 (21 August 2022) + - added k_lms sampling. + **Please run "conda env update -f environment.yaml" to load the k_lms dependencies!!** + - use half precision arithmetic by default, resulting in faster execution and lower memory requirements Pass argument --full_precision to dream.py to get slower but more accurate image generation - ## Installation There are separate installation walkthroughs for [Linux/Mac](#linuxmac) and [Windows](#windows). @@ -379,38 +469,48 @@ There are separate installation walkthroughs for [Linux/Mac](#linuxmac) and [Win ### Linux/Mac 1. You will need to install the following prerequisites if they are not already available. Use your -operating system's preferred installer -* Python (version 3.8.5 recommended; higher may work) -* git + operating system's preferred installer + +- Python (version 3.8.5 recommended; higher may work) +- git 2. Install the Python Anaconda environment manager using pip3. + ``` ~$ pip3 install anaconda ``` + After installing anaconda, you should log out of your system and log back in. If the installation worked, your command prompt will be prefixed by the name of the current anaconda environment, "(base)". 3. Copy the stable-diffusion source code from GitHub: + ``` (base) ~$ git clone https://github.com/lstein/stable-diffusion.git ``` + This will create stable-diffusion folder where you will follow the rest of the steps. 4. Enter the newly-created stable-diffusion folder. From this step forward make sure that you are working in the stable-diffusion directory! + ``` (base) ~$ cd stable-diffusion (base) ~/stable-diffusion$ ``` + 5. Use anaconda to copy necessary python packages, create a new python environment named "ldm", -and activate the environment. + and activate the environment. + ``` (base) ~/stable-diffusion$ conda env create -f environment.yaml (base) ~/stable-diffusion$ conda activate ldm (ldm) ~/stable-diffusion$ ``` + After these steps, your command prompt will be prefixed by "(ldm)" as shown above. 6. Load a couple of small machine-learning models required by stable diffusion: + ``` (ldm) ~/stable-diffusion$ python3 scripts/preload_models.py ``` @@ -430,13 +530,14 @@ to a page that prompts you to click the "download" link. Save the file somewhere Now run the following commands from within the stable-diffusion directory. This will create a symbolic link from the stable-diffusion model.ckpt file, to the true location of the sd-v1-4.ckpt file. - + ``` (ldm) ~/stable-diffusion$ mkdir -p models/ldm/stable-diffusion-v1 (ldm) ~/stable-diffusion$ ln -sf /path/to/sd-v1-4.ckpt models/ldm/stable-diffusion-v1/model.ckpt ``` 8. Start generating images! + ``` # for the pre-release weights use the -l or --liaon400m switch (ldm) ~/stable-diffusion$ python3 scripts/dream.py -l @@ -447,15 +548,18 @@ link from the stable-diffusion model.ckpt file, to the true location of the sd-v # for additional configuration switches and arguments, use -h or --help (ldm) ~/stable-diffusion$ python3 scripts/dream.py -h ``` -9. Subsequently, to relaunch the script, be sure to run "conda activate ldm" (step 5, second command), enter the "stable-diffusion" -directory, and then launch the dream script (step 8). If you forget to activate the ldm environment, the script will fail with multiple ModuleNotFound errors. + +9. Subsequently, to relaunch the script, be sure to run "conda activate ldm" (step 5, second command), enter the "stable-diffusion" + directory, and then launch the dream script (step 8). If you forget to activate the ldm environment, the script will fail with multiple ModuleNotFound errors. #### Updating to newer versions of the script This distribution is changing rapidly. If you used the "git clone" method (step 5) to download the stable-diffusion directory, then to update to the latest and greatest version, launch the Anaconda window, enter "stable-diffusion", and type: + ``` (ldm) ~/stable-diffusion$ git pull ``` + This will bring your local copy into sync with the remote one. ### Windows @@ -467,24 +571,30 @@ This will bring your local copy into sync with the remote one. 3. Launch Anaconda from the Windows Start menu. This will bring up a command window. Type all the remaining commands in this window. 4. Run the command: + ``` git clone https://github.com/lstein/stable-diffusion.git ``` + This will create stable-diffusion folder where you will follow the rest of the steps. 5. Enter the newly-created stable-diffusion folder. From this step forward make sure that you are working in the stable-diffusion directory! + ``` cd stable-diffusion ``` 6. Run the following two commands: + ``` conda env create -f environment.yaml (step 6a) conda activate ldm (step 6b) ``` + This will install all python requirements and activate the "ldm" environment which sets PATH and other environment variables properly. 7. Run the command: + ``` python scripts\preload_models.py ``` @@ -497,30 +607,32 @@ downloaded just-in-time) 8. Now you need to install the weights for the big stable diffusion model. For running with the released weights, you will first need to set up -an acount with Hugging Face (https://huggingface.co). Use your +an acount with Hugging Face (https://huggingface.co). Use your credentials to log in, and then point your browser at -https://huggingface.co/CompVis/stable-diffusion-v-1-4-original. You +https://huggingface.co/CompVis/stable-diffusion-v-1-4-original. You may be asked to sign a license agreement at this point. Click on "Files and versions" near the top of the page, and then click on the file named "sd-v1-4.ckpt". You'll be taken to a page that prompts you to click the "download" link. Now save the file somewhere -safe on your local machine. The weight file is >4 GB in size, so +safe on your local machine. The weight file is >4 GB in size, so downloading may take a while. Now run the following commands from **within the stable-diffusion directory** to copy the weights file to the right place: - + ``` mkdir -p models\ldm\stable-diffusion-v1 copy C:\path\to\sd-v1-4.ckpt models\ldm\stable-diffusion-v1\model.ckpt ``` + Please replace "C:\path\to\sd-v1.4.ckpt" with the correct path to wherever -you stashed this file. If you prefer not to copy or move the .ckpt file, +you stashed this file. If you prefer not to copy or move the .ckpt file, you may instead create a shortcut to it from within "models\ldm\stable-diffusion-v1\". 9. Start generating images! + ``` # for the pre-release weights python scripts\dream.py -l @@ -528,14 +640,17 @@ python scripts\dream.py -l # for the post-release weights python scripts\dream.py ``` + 10. Subsequently, to relaunch the script, first activate the Anaconda command window (step 3), enter the stable-diffusion directory (step 5, "cd \path\to\stable-diffusion"), run "conda activate ldm" (step 6b), and then launch the dream script (step 9). #### Updating to newer versions of the script This distribution is changing rapidly. If you used the "git clone" method (step 5) to download the stable-diffusion directory, then to update to the latest and greatest version, launch the Anaconda window, enter "stable-diffusion", and type: + ``` git pull ``` + This will bring your local copy into sync with the remote one. ## Simplified API for text to image generation @@ -544,22 +659,21 @@ For programmers who wish to incorporate stable-diffusion into other products, this repository includes a simplified API for text to image generation, which lets you create images from a prompt in just three lines of code: -~~~~ +``` from ldm.simplet2i import T2I model = T2I() outputs = model.txt2img("a unicorn in manhattan") -~~~~ +``` Outputs is a list of lists in the format [[filename1,seed1],[filename2,seed2]...] Please see ldm/simplet2i.py for more information. - ## Workaround for machines with limited internet connectivity My development machine is a GPU node in a high-performance compute cluster which has no connection to the internet. During model initialization, stable-diffusion tries to download the Bert tokenizer -and a file needed by the kornia library. This obviously didn't work +and a file needed by the kornia library. This obviously didn't work for me. To work around this, I have modified ldm/modules/encoders/modules.py @@ -570,7 +684,7 @@ prior to running the code on an isolated one. This assumes that both machines share a common network-mounted filesystem with a common .cache directory. -~~~~ +``` (ldm) ~/stable-diffusion$ python3 ./scripts/preload_models.py preloading bert tokenizer... Downloading: 100%|██████████████████████████████████| 28.0/28.0 [00:00<00:00, 49.3kB/s] @@ -582,7 +696,7 @@ preloading kornia requirements... Downloading: "https://github.com/DagnyT/hardnet/raw/master/pretrained/train_liberty_with_aug/checkpoint_liberty_with_aug.pth" to /u/lstein/.cache/torch/hub/checkpoints/checkpoint_liberty_with_aug.pth 100%|███████████████████████████████████████████████| 5.10M/5.10M [00:00<00:00, 101MB/s] ...success -~~~~ +``` If you don't need this change and want to download the files just in time, copy over the file ldm/modules/encoders/modules.py from the @@ -595,16 +709,15 @@ For support, please use this repository's GitHub Issues tracking service. Feel free to send me an email if you use and like the script. -*Original Author:* Lincoln D. Stein +_Original Author:_ Lincoln D. Stein -*Contributions by:* +_Contributions by:_ [Peter Kowalczyk](https://github.com/slix), [Henry Harrison](https://github.com/hwharrison), [xraxra](https://github.com/xraxra), [bmaltais](https://github.com/bmaltais), [Sean McLellan](https://github.com/Oceanswave), [nicolai256](https://github.com/nicolai256), [Benjamin Warner](https://github.com/warner-benjamin), -[tildebyte](https://github.com/tildebyte), +[tildebyte](https://github.com/tildebyte),[yunsaki](https://github.com/yunsaki) and [Tesseract Cat](https://github.com/TesseractCat) - Original portions of the software are Copyright (c) 2020 Lincoln D. Stein (https://github.com/lstein) #Further Reading diff --git a/Stable_Diffusion_AI_Notebook.ipynb b/Stable_Diffusion_AI_Notebook.ipynb new file mode 100644 index 0000000000..defc158346 --- /dev/null +++ b/Stable_Diffusion_AI_Notebook.ipynb @@ -0,0 +1,256 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "Stable_Diffusion_AI_Notebook.ipynb", + "provenance": [], + "collapsed_sections": [], + "private_outputs": true + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "accelerator": "GPU", + "gpuClass": "standard" + }, + "cells": [ + { + "cell_type": "markdown", + "source": [ + "# Stable Diffusion AI Notebook\n", + "\n", + "\"stable-diffusion-ai\"
\n", + "#### Instructions:\n", + "1. Execute each cell in order to mount a Dream bot and create images from text.
\n", + "2. Once cells 1-8 were run correctly you'll be executing a terminal in cell #9, you'll to enter `pipenv run scripts/dream.py` command to run Dream bot.
\n", + "3. After launching dream bot, you'll see:
`Dream > ` in terminal.
Insert a command, eg. `Dream > Astronaut floating in a distant galaxy`, or type `-h` for help.\n", + "3. After completion you'll see your generated images in path `stable-diffusion/outputs/img-samples/`, you can also display images in cell #10.\n", + "4. To quit Dream bot use `q` command.
\n", + "---\n", + "Note: It takes some time to load, but after installing all dependencies you can use the bot all time you want while colab instance is up.
\n", + "Requirements: For this notebook to work you need to have [Stable-Diffusion-v-1-4](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original) stored in your Google Drive, it will be needed in cell #6\n", + "##### For more details visit Github repository: [lstein/stable-diffusion](https://github.com/lstein/stable-diffusion)\n", + "---\n" + ], + "metadata": { + "id": "ycYWcsEKc6w7" + } + }, + { + "cell_type": "code", + "source": [ + "#@title 1. Check current GPU assigned\n", + "!nvidia-smi -L\n", + "!nvidia-smi" + ], + "metadata": { + "cellView": "form", + "id": "a2Z5Qu_o8VtQ" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "cellView": "form", + "id": "vbI9ZsQHzjqF" + }, + "outputs": [], + "source": [ + "#@title 2. Download stable-diffusion Repository\n", + "from os.path import exists\n", + "\n", + "if exists(\"/content/stable-diffusion/\")==True:\n", + " print(\"Already downloaded repo\")\n", + "else:\n", + " !git clone --quiet https://github.com/lstein/stable-diffusion.git # Original repo\n", + " %cd stable-diffusion/\n", + " !git checkout --quiet tags/release-1.09\n", + " " + ] + }, + { + "cell_type": "code", + "source": [ + "#@title 3. Install Python 3.8 \n", + "%%capture --no-stderr\n", + "import gc\n", + "!apt-get -qq install python3.8\n", + "gc.collect()" + ], + "metadata": { + "id": "daHlozvwKesj", + "cellView": "form" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "#@title 4. Install dependencies from file in a VirtualEnv\n", + "#@markdown Be patient, it takes ~ 5 - 7min
\n", + "%%capture --no-stderr\n", + "#Virtual environment\n", + "!pip install pipenv -q\n", + "!pip install colab-xterm\n", + "%load_ext colabxterm\n", + "!pipenv --python 3.8\n", + "!pipenv install -r requirements.txt --skip-lock\n", + "gc.collect()\n" + ], + "metadata": { + "cellView": "form", + "id": "QbXcGXYEFSNB" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "#@title 5. Mount google Drive\n", + "from google.colab import drive\n", + "drive.mount('/content/drive')" + ], + "metadata": { + "cellView": "form", + "id": "YEWPV-sF1RDM" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "#@title 6. Drive Path to model\n", + "#@markdown Path should start with /content/drive/path-to-your-file
\n", + "#@markdown Note: Model should be downloaded from https://huggingface.co
\n", + "#@markdown Lastest release: [Stable-Diffusion-v-1-4](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original)\n", + "from os.path import exists\n", + "\n", + "model_path = \"\" #@param {type:\"string\"}\n", + "if exists(model_path)==True:\n", + " print(\"✅ Valid directory\")\n", + "else: \n", + " print(\"❌ File doesn't exist\")" + ], + "metadata": { + "cellView": "form", + "id": "zRTJeZ461WGu" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "#@title 7. Symlink to model\n", + "\n", + "from os.path import exists\n", + "import os \n", + "\n", + "# Folder creation if it doesn't exist\n", + "if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1\")==True:\n", + " print(\"❗ Dir stable-diffusion-v1 already exists\")\n", + "else:\n", + " %mkdir /content/stable-diffusion/models/ldm/stable-diffusion-v1\n", + " print(\"✅ Dir stable-diffusion-v1 created\")\n", + "\n", + "# Symbolic link if it doesn't exist\n", + "if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt\")==True:\n", + " print(\"❗ Symlink already created\")\n", + "else: \n", + " src = model_path\n", + " dst = '/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt'\n", + " os.symlink(src, dst) \n", + " print(\"✅ Symbolic link created successfully\")" + ], + "metadata": { + "id": "UY-NNz4I8_aG", + "cellView": "form" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "#@title 8. Load small ML models required\n", + "%%capture --no-stderr\n", + "!pipenv run scripts/preload_models.py\n", + "gc.collect()" + ], + "metadata": { + "cellView": "form", + "id": "ChIDWxLVHGGJ" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "#@title 9. Run Terminal and Execute Dream bot\n", + "#@markdown Steps:
\n", + "#@markdown 1. Execute command `pipenv run scripts/dream.py` to run dream bot.
\n", + "#@markdown 2. After initialized you'll see `Dream>` line.
\n", + "#@markdown 3. Example text: `Astronaut floating in a distant galaxy`
\n", + "#@markdown 4. To quit Dream bot use: `q` command.
\n", + "\n", + "#Run from virtual env\n", + "\n", + "%xterm\n", + "gc.collect()" + ], + "metadata": { + "id": "ir4hCrMIuUpl", + "cellView": "form" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "#@title 10. Show generated images\n", + "\n", + "import glob\n", + "import matplotlib.pyplot as plt\n", + "import matplotlib.image as mpimg\n", + "%matplotlib inline\n", + "\n", + "images = []\n", + "for img_path in glob.glob('/content/stable-diffusion/outputs/img-samples/*.png'):\n", + " images.append(mpimg.imread(img_path))\n", + "\n", + "# Remove ticks and labels on x-axis and y-axis both\n", + "\n", + "plt.figure(figsize=(20,10))\n", + "\n", + "columns = 5\n", + "for i, image in enumerate(images):\n", + " ax = plt.subplot(len(images) / columns + 1, columns, i + 1)\n", + " ax.axes.xaxis.set_visible(False)\n", + " ax.axes.yaxis.set_visible(False)\n", + " ax.axis('off')\n", + " plt.imshow(image)\n", + " gc.collect()\n", + "\n" + ], + "metadata": { + "cellView": "form", + "id": "qnLohSHmKoGk" + }, + "execution_count": null, + "outputs": [] + } + ] +} \ No newline at end of file diff --git a/ldm/dream/pngwriter.py b/ldm/dream/pngwriter.py index 3a3f205512..584d4479ba 100644 --- a/ldm/dream/pngwriter.py +++ b/ldm/dream/pngwriter.py @@ -14,6 +14,8 @@ from math import sqrt, floor, ceil from PIL import Image, PngImagePlugin # -------------------image generation utils----- + + class PngWriter: def __init__(self, outdir, prompt=None, batch_size=1): self.outdir = outdir @@ -23,18 +25,19 @@ class PngWriter: self.files_written = [] os.makedirs(outdir, exist_ok=True) - def write_image(self, image, seed): + def write_image(self, image, seed, upscaled=False): self.filepath = self.unique_filename( - seed, self.filepath + seed, upscaled, self.filepath ) # will increment name in some sensible way try: prompt = f'{self.prompt} -S{seed}' self.save_image_and_prompt_to_png(image, prompt, self.filepath) except IOError as e: print(e) - self.files_written.append([self.filepath, seed]) + if not upscaled: + self.files_written.append([self.filepath, seed]) - def unique_filename(self, seed, previouspath=None): + def unique_filename(self, seed, upscaled=False, previouspath=None): revision = 1 if previouspath is None: @@ -57,7 +60,7 @@ class PngWriter: basename = os.path.basename(previouspath) x = re.match('^(\d+)\..*\.png', basename) if not x: - return self.unique_filename(seed, previouspath) + return self.unique_filename(seed, upscaled, previouspath) basecount = int(x.groups()[0]) series = 0 @@ -65,13 +68,12 @@ class PngWriter: while not finished: series += 1 filename = f'{basecount:06}.{seed}.png' - if self.batch_size > 1 or os.path.exists( - os.path.join(self.outdir, filename) - ): + path = os.path.join(self.outdir, filename) + if self.batch_size > 1 or os.path.exists(path): + if upscaled: + break filename = f'{basecount:06}.{seed}.{series:02}.png' - finished = not os.path.exists( - os.path.join(self.outdir, filename) - ) + finished = not os.path.exists(path) return os.path.join(self.outdir, filename) def save_image_and_prompt_to_png(self, image, prompt, path): @@ -84,14 +86,17 @@ class PngWriter: if None in (rows, cols): rows = floor(sqrt(image_cnt)) # try to make it square cols = ceil(image_cnt / rows) - width = image_list[0].width + width = image_list[0].width height = image_list[0].height grid_img = Image.new('RGB', (width * cols, height * rows)) + i = 0 for r in range(0, rows): for c in range(0, cols): - i = r * rows + c + if i>=len(image_list): + break grid_img.paste(image_list[i], (c * width, r * height)) + i = i + 1 return grid_img @@ -101,6 +106,8 @@ class PromptFormatter: self.t2i = t2i self.opt = opt + # note: the t2i object should provide all these values. + # there should be no need to or against opt values def normalize_prompt(self): """Normalize the prompt and switches""" t2i = self.t2i @@ -113,13 +120,15 @@ class PromptFormatter: switches.append(f'-W{opt.width or t2i.width}') switches.append(f'-H{opt.height or t2i.height}') switches.append(f'-C{opt.cfg_scale or t2i.cfg_scale}') - switches.append(f'-m{t2i.sampler_name}') + switches.append(f'-A{opt.sampler_name or t2i.sampler_name}') if opt.init_img: switches.append(f'-I{opt.init_img}') if opt.strength and opt.init_img is not None: switches.append(f'-f{opt.strength or t2i.strength}') if opt.gfpgan_strength: switches.append(f'-G{opt.gfpgan_strength}') + if opt.upscale: + switches.append(f'-U {" ".join([str(u) for u in opt.upscale])}') if t2i.full_precision: switches.append('-F') return ' '.join(switches) diff --git a/ldm/dream/server.py b/ldm/dream/server.py new file mode 100644 index 0000000000..efe3139f74 --- /dev/null +++ b/ldm/dream/server.py @@ -0,0 +1,149 @@ +import json +import base64 +import mimetypes +import os +from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer +from ldm.dream.pngwriter import PngWriter + +class DreamServer(BaseHTTPRequestHandler): + model = None + + def do_GET(self): + if self.path == "/": + self.send_response(200) + self.send_header("Content-type", "text/html") + self.end_headers() + with open("./static/dream_web/index.html", "rb") as content: + self.wfile.write(content.read()) + else: + path = "." + self.path + cwd = os.getcwd() + is_in_cwd = os.path.commonprefix((os.path.realpath(path), cwd)) == cwd + if not (is_in_cwd and os.path.exists(path)): + self.send_response(404) + return + mime_type = mimetypes.guess_type(path)[0] + if mime_type is not None: + self.send_response(200) + self.send_header("Content-type", mime_type) + self.end_headers() + with open("." + self.path, "rb") as content: + self.wfile.write(content.read()) + else: + self.send_response(404) + + def do_POST(self): + self.send_response(200) + self.send_header("Content-type", "application/json") + self.end_headers() + + content_length = int(self.headers['Content-Length']) + post_data = json.loads(self.rfile.read(content_length)) + prompt = post_data['prompt'] + initimg = post_data['initimg'] + iterations = int(post_data['iterations']) + steps = int(post_data['steps']) + width = int(post_data['width']) + height = int(post_data['height']) + cfgscale = float(post_data['cfgscale']) + gfpgan_strength = float(post_data['gfpgan_strength']) + upscale_level = post_data['upscale_level'] + upscale_strength = post_data['upscale_strength'] + upscale = [int(upscale_level),float(upscale_strength)] if upscale_level != '' else None + seed = None if int(post_data['seed']) == -1 else int(post_data['seed']) + + print(f"Request to generate with prompt: {prompt}") + # In order to handle upscaled images, the PngWriter needs to maintain state + # across images generated by each call to prompt2img(), so we define it in + # the outer scope of image_done() + config = post_data.copy() # Shallow copy + config['initimg'] = '' + + images_generated = 0 # helps keep track of when upscaling is started + images_upscaled = 0 # helps keep track of when upscaling is completed + pngwriter = PngWriter( + "./outputs/img-samples/", config['prompt'], 1 + ) + + # if upscaling is requested, then this will be called twice, once when + # the images are first generated, and then again when after upscaling + # is complete. The upscaling replaces the original file, so the second + # entry should not be inserted into the image list. + def image_done(image, seed, upscaled=False): + pngwriter.write_image(image, seed, upscaled) + + # Append post_data to log, but only once! + if not upscaled: + current_image = pngwriter.files_written[-1] + with open("./outputs/img-samples/dream_web_log.txt", "a") as log: + log.write(f"{current_image[0]}: {json.dumps(config)}\n") + self.wfile.write(bytes(json.dumps( + {'event':'result', 'files':current_image, 'config':config} + ) + '\n',"utf-8")) + + # control state of the "postprocessing..." message + upscaling_requested = upscale or gfpgan_strength>0 + nonlocal images_generated # NB: Is this bad python style? It is typical usage in a perl closure. + nonlocal images_upscaled # NB: Is this bad python style? It is typical usage in a perl closure. + if upscaled: + images_upscaled += 1 + else: + images_generated +=1 + if upscaling_requested: + action = None + if images_generated >= iterations: + if images_upscaled < iterations: + action = 'upscaling-started' + else: + action = 'upscaling-done' + if action: + x = images_upscaled+1 + self.wfile.write(bytes(json.dumps( + {'event':action,'processed_file_cnt':f'{x}/{iterations}'} + ) + '\n',"utf-8")) + + def image_progress(image, step): + self.wfile.write(bytes(json.dumps( + {'event':'step', 'step':step} + ) + '\n',"utf-8")) + + if initimg is None: + # Run txt2img + self.model.prompt2image(prompt, + iterations=iterations, + cfg_scale = cfgscale, + width = width, + height = height, + seed = seed, + steps = steps, + gfpgan_strength = gfpgan_strength, + upscale = upscale, + step_callback=image_progress, + image_callback=image_done) + else: + # Decode initimg as base64 to temp file + with open("./img2img-tmp.png", "wb") as f: + initimg = initimg.split(",")[1] # Ignore mime type + f.write(base64.b64decode(initimg)) + + # Run img2img + self.model.prompt2image(prompt, + init_img = "./img2img-tmp.png", + iterations = iterations, + cfg_scale = cfgscale, + seed = seed, + steps = steps, + gfpgan_strength=gfpgan_strength, + upscale = upscale, + step_callback=image_progress, + image_callback=image_done) + + # Remove the temp file + os.remove("./img2img-tmp.png") + + print(f"Prompt generated!") + + +class ThreadingDreamServer(ThreadingHTTPServer): + def __init__(self, server_address): + super(ThreadingDreamServer, self).__init__(server_address, DreamServer) diff --git a/ldm/gfpgan/gfpgan_tools.py b/ldm/gfpgan/gfpgan_tools.py new file mode 100644 index 0000000000..f775e33a45 --- /dev/null +++ b/ldm/gfpgan/gfpgan_tools.py @@ -0,0 +1,165 @@ +import torch +import warnings +import os +import sys +import numpy as np + +from PIL import Image +from scripts.dream import create_argv_parser + +arg_parser = create_argv_parser() +opt = arg_parser.parse_args() + + +def _run_gfpgan(image, strength, prompt, seed, upsampler_scale=4): + print(f'\n* GFPGAN - Restoring Faces: {prompt} : seed:{seed}') + with warnings.catch_warnings(): + warnings.filterwarnings('ignore', category=DeprecationWarning) + warnings.filterwarnings('ignore', category=UserWarning) + + try: + model_path = os.path.join(opt.gfpgan_dir, opt.gfpgan_model_path) + if not os.path.isfile(model_path): + raise Exception('GFPGAN model not found at path ' + model_path) + + sys.path.append(os.path.abspath(opt.gfpgan_dir)) + from gfpgan import GFPGANer + + bg_upsampler = _load_gfpgan_bg_upsampler( + opt.gfpgan_bg_upsampler, upsampler_scale, opt.gfpgan_bg_tile + ) + + gfpgan = GFPGANer( + model_path=model_path, + upscale=upsampler_scale, + arch='clean', + channel_multiplier=2, + bg_upsampler=bg_upsampler, + ) + except Exception: + import traceback + + print('Error loading GFPGAN:', file=sys.stderr) + print(traceback.format_exc(), file=sys.stderr) + + if gfpgan is None: + print( + f'GFPGAN not initialized, it must be loaded via the --gfpgan argument' + ) + return image + + image = image.convert('RGB') + + cropped_faces, restored_faces, restored_img = gfpgan.enhance( + np.array(image, dtype=np.uint8), + has_aligned=False, + only_center_face=False, + paste_back=True, + ) + res = Image.fromarray(restored_img) + + if strength < 1.0: + # Resize the image to the new image if the sizes have changed + if restored_img.size != image.size: + image = image.resize(res.size) + res = Image.blend(image, res, strength) + + if torch.cuda.is_available(): + torch.cuda.empty_cache() + gfpgan = None + + return res + + +def _load_gfpgan_bg_upsampler(bg_upsampler, upsampler_scale, bg_tile=400): + if bg_upsampler == 'realesrgan': + if not torch.cuda.is_available(): # CPU + warnings.warn( + 'The unoptimized RealESRGAN is slow on CPU. We do not use it. ' + 'If you really want to use it, please modify the corresponding codes.' + ) + bg_upsampler = None + else: + model_path = { + 2: 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth', + 4: 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth', + } + + if upsampler_scale not in model_path: + return None + + from basicsr.archs.rrdbnet_arch import RRDBNet + from realesrgan import RealESRGANer + + if upsampler_scale == 4: + model = RRDBNet( + num_in_ch=3, + num_out_ch=3, + num_feat=64, + num_block=23, + num_grow_ch=32, + scale=4, + ) + if upsampler_scale == 2: + model = RRDBNet( + num_in_ch=3, + num_out_ch=3, + num_feat=64, + num_block=23, + num_grow_ch=32, + scale=2, + ) + + bg_upsampler = RealESRGANer( + scale=upsampler_scale, + model_path=model_path[upsampler_scale], + model=model, + tile=bg_tile, + tile_pad=10, + pre_pad=0, + half=True, + ) # need to set False in CPU mode + else: + bg_upsampler = None + + return bg_upsampler + + +def real_esrgan_upscale(image, strength, upsampler_scale, prompt, seed): + print( + f'\n* Real-ESRGAN Upscaling: {prompt} : seed:{seed} : scale:{upsampler_scale}x' + ) + + with warnings.catch_warnings(): + warnings.filterwarnings('ignore', category=DeprecationWarning) + warnings.filterwarnings('ignore', category=UserWarning) + + try: + upsampler = _load_gfpgan_bg_upsampler( + opt.gfpgan_bg_upsampler, upsampler_scale, opt.gfpgan_bg_tile + ) + except Exception: + import traceback + + print('Error loading Real-ESRGAN:', file=sys.stderr) + print(traceback.format_exc(), file=sys.stderr) + + output, img_mode = upsampler.enhance( + np.array(image, dtype=np.uint8), + outscale=upsampler_scale, + alpha_upsampler=opt.gfpgan_bg_upsampler, + ) + + res = Image.fromarray(output) + + if strength < 1.0: + # Resize the image to the new image if the sizes have changed + if output.size != image.size: + image = image.resize(res.size) + res = Image.blend(image, res, strength) + + if torch.cuda.is_available(): + torch.cuda.empty_cache() + upsampler = None + + return res diff --git a/ldm/models/diffusion/ksampler.py b/ldm/models/diffusion/ksampler.py index 1da81eee5a..6d463fa6ba 100644 --- a/ldm/models/diffusion/ksampler.py +++ b/ldm/models/diffusion/ksampler.py @@ -61,6 +61,9 @@ class KSampler(object): # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ... **kwargs, ): + def route_callback(k_callback_values): + if img_callback is not None: + img_callback(k_callback_values['x'], k_callback_values['i']) sigmas = self.model.get_sigmas(S) if x_T: @@ -78,7 +81,8 @@ class KSampler(object): } return ( K.sampling.__dict__[f'sample_{self.schedule}']( - model_wrap_cfg, x, sigmas, extra_args=extra_args + model_wrap_cfg, x, sigmas, extra_args=extra_args, + callback=route_callback ), None, ) diff --git a/ldm/modules/embedding_manager.py b/ldm/modules/embedding_manager.py index 677bc4ad3a..128b575e9b 100644 --- a/ldm/modules/embedding_manager.py +++ b/ldm/modules/embedding_manager.py @@ -215,11 +215,13 @@ class EmbeddingManager(nn.Module): ckpt_path, ) - def load(self, ckpt_path): + def load(self, ckpt_path, full=True): ckpt = torch.load(ckpt_path, map_location='cpu') - - self.string_to_token_dict = ckpt['string_to_token'] - self.string_to_param_dict = ckpt['string_to_param'] + self.string_to_token_dict = ckpt["string_to_token"] + self.string_to_param_dict = ckpt["string_to_param"] + if not full: + for key, value in self.string_to_param_dict.items(): + self.string_to_param_dict[key] = torch.nn.Parameter(value.half()) def get_embedding_norms_squared(self): all_params = torch.cat( diff --git a/ldm/simplet2i.py b/ldm/simplet2i.py index 50816ec403..7ec275751e 100644 --- a/ldm/simplet2i.py +++ b/ldm/simplet2i.py @@ -7,7 +7,6 @@ import torch import numpy as np import random -import sys import os from omegaconf import OmegaConf from PIL import Image @@ -21,7 +20,7 @@ from contextlib import contextmanager, nullcontext import transformers import time import re -import traceback +import sys from ldm.util import instantiate_from_config from ldm.models.diffusion.ddim import DDIMSampler @@ -123,6 +122,7 @@ class T2I: cfg_scale=7.5, weights='models/ldm/stable-diffusion-v1/model.ckpt', config='configs/stable-diffusion/v1-inference.yaml', + grid=False, width=512, height=512, sampler_name='klms', @@ -133,9 +133,9 @@ class T2I: full_precision=False, strength=0.75, # default in scripts/img2img.py embedding_path=None, - latent_diffusion_weights=False, # just to keep track of this parameter when regenerating prompt + # just to keep track of this parameter when regenerating prompt + latent_diffusion_weights=False, device='cuda', - gfpgan=None, ): self.batch_size = batch_size self.iterations = iterations @@ -148,6 +148,7 @@ class T2I: self.sampler_name = sampler_name self.latent_channels = latent_channels self.downsampling_factor = downsampling_factor + self.grid = grid self.ddim_eta = ddim_eta self.precision = precision self.full_precision = full_precision @@ -157,7 +158,8 @@ class T2I: self.sampler = None self.latent_diffusion_weights = latent_diffusion_weights self.device = device - self.gfpgan = gfpgan + + self.session_peakmem = torch.cuda.max_memory_allocated() if seed is None: self.seed = self._new_seed() else: @@ -175,16 +177,15 @@ class T2I: outdir, prompt, kwargs.get('batch_size', self.batch_size) ) for r in results: - metadata_str = f'prompt2png("{prompt}" {kwargs} seed={r[1]}' # gets written into the PNG pngwriter.write_image(r[0], r[1]) return pngwriter.files_written def txt2img(self, prompt, **kwargs): - outdir = kwargs.get('outdir', 'outputs/img-samples') + outdir = kwargs.pop('outdir', 'outputs/img-samples') return self.prompt2png(prompt, outdir, **kwargs) def img2img(self, prompt, **kwargs): - outdir = kwargs.get('outdir', 'outputs/img-samples') + outdir = kwargs.pop('outdir', 'outputs/img-samples') assert ( 'init_img' in kwargs ), 'call to img2img() must include the init_img argument' @@ -202,14 +203,18 @@ class T2I: ddim_eta=None, skip_normalize=False, image_callback=None, + step_callback=None, # these are specific to txt2img width=None, height=None, # these are specific to img2img init_img=None, strength=None, - gfpgan_strength=None, + gfpgan_strength=0, + save_original=False, + upscale=None, variants=None, + sampler_name=None, **args, ): # eat up additional cruft """ @@ -228,9 +233,14 @@ class T2I: gfpgan_strength // strength for GFPGAN. 0.0 preserves image exactly, 1.0 replaces it completely ddim_eta // image randomness (eta=0.0 means the same seed always produces the same image) variants // if >0, the 1st generated image will be passed back to img2img to generate the requested number of variants + step_callback // a function or method that will be called each step image_callback // a function or method that will be called each time an image is generated - To use the callback, define a function of method that receives two arguments, an Image object + To use the step callback, define a function that receives two arguments: + - Image GPU data + - The step number + + To use the image callback, define a function of method that receives two arguments, an Image object and the seed. You can then do whatever you like with the image, including converting it to different formats and manipulating it. For example: @@ -262,14 +272,19 @@ class T2I: h = int(height / 64) * 64 if h != height or w != width: print( - f'Height and width must be multiples of 64. Resizing to {h}x{w}' + f'Height and width must be multiples of 64. Resizing to {h}x{w}.' ) height = h width = w scope = autocast if self.precision == 'autocast' else nullcontext + if sampler_name and (sampler_name != self.sampler_name): + self.sampler_name = sampler_name + self._set_sampler() + tic = time.time() + torch.cuda.torch.cuda.reset_peak_memory_stats() results = list() try: @@ -285,6 +300,7 @@ class T2I: skip_normalize=skip_normalize, init_img=init_img, strength=strength, + callback=step_callback, ) else: images_iterator = self._txt2img( @@ -297,32 +313,54 @@ class T2I: skip_normalize=skip_normalize, width=width, height=height, + callback=step_callback, ) with scope(self.device.type), self.model.ema_scope(): - for n in trange(iterations, desc='Sampling'): + for n in trange(iterations, desc='Generating'): seed_everything(seed) iter_images = next(images_iterator) for image in iter_images: - try: - # if gfpgan strength is none or less than or equal to 0.0 then - # don't even attempt to use GFPGAN. - # if the user specified a value of -G that satisifies the condition and - # --gfpgan wasn't specified, at startup then - # the net result is a message gets printed - nothing else happens. - if gfpgan_strength is not None and gfpgan_strength > 0.0: - image = self._run_gfpgan( - image, gfpgan_strength - ) - except Exception as e: - print( - f'Error running GFPGAN - Your image was not enhanced.\n{e}' - ) results.append([image, seed]) if image_callback is not None: image_callback(image, seed) seed = self._new_seed() + if upscale is not None or gfpgan_strength > 0: + for result in results: + image, seed = result + try: + if upscale is not None: + from ldm.gfpgan.gfpgan_tools import ( + real_esrgan_upscale, + ) + if len(upscale) < 2: + upscale.append(0.75) + image = real_esrgan_upscale( + image, + upscale[1], + int(upscale[0]), + prompt, + seed, + ) + if gfpgan_strength > 0: + from ldm.gfpgan.gfpgan_tools import _run_gfpgan + + image = _run_gfpgan( + image, gfpgan_strength, prompt, seed, 1 + ) + except Exception as e: + print( + f'Error running RealESRGAN - Your image was not upscaled.\n{e}' + ) + if image_callback is not None: + if save_original: + image_callback(image, seed) + else: + image_callback(image, seed, upscaled=True) + else: # no callback passed, so we simply replace old image with rescaled one + result[0] = image + except KeyboardInterrupt: print('*interrupted*') print( @@ -333,7 +371,21 @@ class T2I: print('Are you sure your system has an adequate NVIDIA GPU?') toc = time.time() - print(f'{len(results)} images generated in', '%4.2fs' % (toc - tic)) + self.session_peakmem = max( + self.session_peakmem, torch.cuda.max_memory_allocated() + ) + print('Usage stats:') + print( + f' {len(results)} image(s) generated in', '%4.2fs' % (toc - tic) + ) + print( + f' Max VRAM used for this generation:', + '%4.2fG' % (torch.cuda.max_memory_allocated() / 1e9), + ) + print( + f' Max VRAM used since script start: ', + '%4.2fG' % (self.session_peakmem / 1e9), + ) return results @torch.no_grad() @@ -348,6 +400,7 @@ class T2I: skip_normalize, width, height, + callback, ): """ An infinite iterator of images from the prompt. @@ -371,6 +424,7 @@ class T2I: unconditional_guidance_scale=cfg_scale, unconditional_conditioning=uc, eta=ddim_eta, + img_callback=callback ) yield self._samples_to_images(samples) @@ -386,6 +440,7 @@ class T2I: skip_normalize, init_img, strength, + callback, # Currently not implemented for img2img ): """ An infinite iterator of images from the prompt and the initial image @@ -492,46 +547,50 @@ class T2I: self.device = self._get_device() model = self._load_model_from_config(config, self.weights) if self.embedding_path is not None: - model.embedding_manager.load(self.embedding_path) + model.embedding_manager.load( + self.embedding_path, self.full_precision + ) self.model = model.to(self.device) # model.to doesn't change the cond_stage_model.device used to move the tokenizer output, so set it here self.model.cond_stage_model.device = self.device except AttributeError: + import traceback + print('Error loading model. Only the CUDA backend is supported',file=sys.stderr) + print(traceback.format_exc(),file=sys.stderr) raise SystemExit - msg = f'setting sampler to {self.sampler_name}' - if self.sampler_name == 'plms': - self.sampler = PLMSSampler(self.model, device=self.device) - elif self.sampler_name == 'ddim': - self.sampler = DDIMSampler(self.model, device=self.device) - elif self.sampler_name == 'k_dpm_2_a': - self.sampler = KSampler( - self.model, 'dpm_2_ancestral', device=self.device - ) - elif self.sampler_name == 'k_dpm_2': - self.sampler = KSampler( - self.model, 'dpm_2', device=self.device - ) - elif self.sampler_name == 'k_euler_a': - self.sampler = KSampler( - self.model, 'euler_ancestral', device=self.device - ) - elif self.sampler_name == 'k_euler': - self.sampler = KSampler( - self.model, 'euler', device=self.device - ) - elif self.sampler_name == 'k_heun': - self.sampler = KSampler(self.model, 'heun', device=self.device) - elif self.sampler_name == 'k_lms': - self.sampler = KSampler(self.model, 'lms', device=self.device) - else: - msg = f'unsupported sampler {self.sampler_name}, defaulting to plms' - self.sampler = PLMSSampler(self.model, device=self.device) - - print(msg) + self._set_sampler() return self.model + def _set_sampler(self): + msg = f'>> Setting Sampler to {self.sampler_name}' + if self.sampler_name == 'plms': + self.sampler = PLMSSampler(self.model, device=self.device) + elif self.sampler_name == 'ddim': + self.sampler = DDIMSampler(self.model, device=self.device) + elif self.sampler_name == 'k_dpm_2_a': + self.sampler = KSampler( + self.model, 'dpm_2_ancestral', device=self.device + ) + elif self.sampler_name == 'k_dpm_2': + self.sampler = KSampler(self.model, 'dpm_2', device=self.device) + elif self.sampler_name == 'k_euler_a': + self.sampler = KSampler( + self.model, 'euler_ancestral', device=self.device + ) + elif self.sampler_name == 'k_euler': + self.sampler = KSampler(self.model, 'euler', device=self.device) + elif self.sampler_name == 'k_heun': + self.sampler = KSampler(self.model, 'heun', device=self.device) + elif self.sampler_name == 'k_lms': + self.sampler = KSampler(self.model, 'lms', device=self.device) + else: + msg = f'>> Unsupported Sampler: {self.sampler_name}, Defaulting to plms' + self.sampler = PLMSSampler(self.model, device=self.device) + + print(msg) + def _load_model_from_config(self, config, ckpt): print(f'Loading model from {ckpt}') pl_sd = torch.load(ckpt, map_location='cpu') @@ -548,13 +607,16 @@ class T2I: ) else: print( - 'Using half precision math. Call with --full_precision to use slower but more accurate full precision.' + 'Using half precision math. Call with --full_precision to use more accurate but VRAM-intensive full precision.' ) model.half() return model def _load_img(self, path): - image = Image.open(path).convert('RGB') + print(f'image path = {path}, cwd = {os.getcwd()}') + with Image.open(path) as img: + image = img.convert('RGB') + w, h = image.size print(f'loaded input image of size ({w}, {h}) from {path}') w, h = map( @@ -612,28 +674,3 @@ class T2I: weights.append(1.0) remaining = 0 return prompts, weights - - def _run_gfpgan(self, image, strength): - if self.gfpgan is None: - print( - f'GFPGAN not initialized, it must be loaded via the --gfpgan argument' - ) - return image - - image = image.convert('RGB') - - cropped_faces, restored_faces, restored_img = self.gfpgan.enhance( - np.array(image, dtype=np.uint8), - has_aligned=False, - only_center_face=False, - paste_back=True, - ) - res = Image.fromarray(restored_img) - - if strength < 1.0: - # Resize the image to the new image if the sizes have changed - if restored_img.size != image.size: - image = image.resize(res.size) - res = Image.blend(image, res, strength) - - return res diff --git a/scripts/dream.py b/scripts/dream.py index f703edebbc..59231af3e1 100755 --- a/scripts/dream.py +++ b/scripts/dream.py @@ -9,8 +9,7 @@ import copy import warnings import ldm.dream.readline from ldm.dream.pngwriter import PngWriter, PromptFormatter - -debugging = False +from ldm.dream.server import DreamServer, ThreadingDreamServer def main(): @@ -52,7 +51,9 @@ def main(): weights=weights, full_precision=opt.full_precision, config=config, - latent_diffusion_weights=opt.laion400m, # this is solely for recreating the prompt + grid = opt.grid, + # this is solely for recreating the prompt + latent_diffusion_weights=opt.laion400m, embedding_path=opt.embedding_path, device=opt.device, ) @@ -64,80 +65,50 @@ def main(): # gets rid of annoying messages about random seed logging.getLogger('pytorch_lightning').setLevel(logging.ERROR) + # load the infile as a list of lines infile = None - try: - if opt.infile is not None: - infile = open(opt.infile, 'r') - except FileNotFoundError as e: - print(e) - exit(-1) + if opt.infile: + try: + if os.path.isfile(opt.infile): + infile = open(opt.infile, 'r', encoding='utf-8') + elif opt.infile == '-': # stdin + infile = sys.stdin + else: + raise FileNotFoundError(f'{opt.infile} not found.') + except (FileNotFoundError, IOError) as e: + print(f'{e}. Aborting.') + sys.exit(-1) # preload the model t2i.load_model() - # load GFPGAN if requested - if opt.use_gfpgan: - print('\n* --gfpgan was specified, loading gfpgan...') - with warnings.catch_warnings(): - warnings.filterwarnings('ignore', category=DeprecationWarning) + if not infile: + print( + "\n* Initialization done! Awaiting your command (-h for help, 'q' to quit)" + ) - try: - model_path = os.path.join( - opt.gfpgan_dir, opt.gfpgan_model_path - ) - if not os.path.isfile(model_path): - raise Exception( - 'GFPGAN model not found at path ' + model_path - ) - - sys.path.append(os.path.abspath(opt.gfpgan_dir)) - from gfpgan import GFPGANer - - bg_upsampler = load_gfpgan_bg_upsampler( - opt.gfpgan_bg_upsampler, opt.gfpgan_bg_tile - ) - - t2i.gfpgan = GFPGANer( - model_path=model_path, - upscale=opt.gfpgan_upscale, - arch='clean', - channel_multiplier=2, - bg_upsampler=bg_upsampler, - ) - except Exception: - import traceback - - print('Error loading GFPGAN:', file=sys.stderr) - print(traceback.format_exc(), file=sys.stderr) - - print( - "\n* Initialization done! Awaiting your command (-h for help, 'q' to quit, 'cd' to change output dir, 'pwd' to print output dir)..." - ) - - log_path = os.path.join(opt.outdir, 'dream_log.txt') - with open(log_path, 'a') as log: - cmd_parser = create_cmd_parser() - main_loop(t2i, opt.outdir, cmd_parser, log, infile) - log.close() - if infile: - infile.close() + cmd_parser = create_cmd_parser() + if opt.web: + dream_server_loop(t2i) + else: + main_loop(t2i, opt.outdir, cmd_parser, infile) -def main_loop(t2i, outdir, parser, log, infile): +def main_loop(t2i, outdir, parser, infile): """prompt/read/execute loop""" done = False last_seeds = [] while not done: try: - command = infile.readline() if infile else input('dream> ') + command = get_next_command(infile) except EOFError: done = True break - if infile and len(command) == 0: - done = True - break + # skip empty lines + if not command.strip(): + continue if command.startswith(('#', '//')): continue @@ -152,25 +123,10 @@ def main_loop(t2i, outdir, parser, log, infile): print(str(e)) continue - if len(elements) == 0: - continue - if elements[0] == 'q': done = True break - if elements[0] == 'cd' and len(elements) > 1: - if os.path.exists(elements[1]): - print(f'setting image output directory to {elements[1]}') - outdir = elements[1] - else: - print(f'directory {elements[1]} does not exist') - continue - - if elements[0] == 'pwd': - print(f'current output directory is {outdir}') - continue - if elements[0].startswith( '!dream' ): # in case a stored prompt still contains the !dream command @@ -207,18 +163,26 @@ def main_loop(t2i, outdir, parser, log, infile): opt.seed = None normalized_prompt = PromptFormatter(t2i, opt).normalize_prompt() - individual_images = not opt.grid + do_grid = opt.grid or t2i.grid + individual_images = not do_grid + if opt.outdir: + if not os.path.exists(opt.outdir): + os.makedirs(opt.outdir) + current_outdir = opt.outdir + else: + current_outdir = outdir + + # Here is where the images are actually generated! try: - file_writer = PngWriter(outdir, normalized_prompt, opt.batch_size) - callback = file_writer.write_image if individual_images else None - - image_list = t2i.prompt2image(image_callback=callback, **vars(opt)) + file_writer = PngWriter(current_outdir, normalized_prompt, opt.batch_size) + callback = file_writer.write_image if individual_images else None + image_list = t2i.prompt2image(image_callback=callback, **vars(opt)) results = ( file_writer.files_written if individual_images else image_list ) - if opt.grid and len(results) > 0: + if do_grid and len(results) > 0: grid_img = file_writer.make_grid([r[0] for r in results]) filename = file_writer.unique_filename(results[0][1]) seeds = [a[1] for a in results] @@ -239,94 +203,74 @@ def main_loop(t2i, outdir, parser, log, infile): continue print('Outputs:') - write_log_message(t2i, normalized_prompt, results, log) + log_path = os.path.join(current_outdir, 'dream_log.txt') + write_log_message(normalized_prompt, results, log_path) print('goodbye!') -def load_gfpgan_bg_upsampler(bg_upsampler, bg_tile=400): - import torch - - if bg_upsampler == 'realesrgan': - if not torch.cuda.is_available(): # CPU - import warnings - - warnings.warn( - 'The unoptimized RealESRGAN is slow on CPU. We do not use it. ' - 'If you really want to use it, please modify the corresponding codes.' - ) - bg_upsampler = None - else: - from basicsr.archs.rrdbnet_arch import RRDBNet - from realesrgan import RealESRGANer - - model = RRDBNet( - num_in_ch=3, - num_out_ch=3, - num_feat=64, - num_block=23, - num_grow_ch=32, - scale=2, - ) - bg_upsampler = RealESRGANer( - scale=2, - model_path='https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth', - model=model, - tile=bg_tile, - tile_pad=10, - pre_pad=0, - half=True, - ) # need to set False in CPU mode +def get_next_command(infile=None) -> str: #command string + if infile is None: + command = input('dream> ') else: - bg_upsampler = None + command = infile.readline() + if not command: + raise EOFError + else: + command = command.strip() + print(f'#{command}') + return command - return bg_upsampler +def dream_server_loop(t2i): + print('\n* --web was specified, starting web server...') + # Change working directory to the stable-diffusion directory + os.chdir( + os.path.abspath(os.path.join(os.path.dirname(__file__), '..')) + ) + + # Start server + DreamServer.model = t2i + dream_server = ThreadingDreamServer(("0.0.0.0", 9090)) + print("\nStarted Stable Diffusion dream server!") + print("Point your browser at http://localhost:9090 or use the host's DNS name or IP address.") + + try: + dream_server.serve_forever() + except KeyboardInterrupt: + pass + + dream_server.server_close() -# variant generation is going to be superseded by a generalized -# "prompt-morph" functionality -# def generate_variants(t2i,outdir,opt,previous_gens): -# variants = [] -# print(f"Generating {opt.variants} variant(s)...") -# newopt = copy.deepcopy(opt) -# newopt.iterations = 1 -# newopt.variants = None -# for r in previous_gens: -# newopt.init_img = r[0] -# prompt = PromptFormatter(t2i,newopt).normalize_prompt() -# print(f"] generating variant for {newopt.init_img}") -# for j in range(0,opt.variants): -# try: -# file_writer = PngWriter(outdir,prompt,newopt.batch_size) -# callback = file_writer.write_image -# t2i.prompt2image(image_callback=callback,**vars(newopt)) -# results = file_writer.files_written -# variants.append([prompt,results]) -# except AssertionError as e: -# print(e) -# continue -# print(f'{opt.variants} variants generated') -# return variants +def write_log_message(prompt, results, log_path): + """logs the name of the output image, prompt, and prompt args to the terminal and log file""" + log_lines = [f'{r[0]}: {prompt} -S{r[1]}\n' for r in results] + print(*log_lines, sep='') + + with open(log_path, 'a', encoding='utf-8') as file: + file.writelines(log_lines) -def write_log_message(t2i, prompt, results, logfile): - """logs the name of the output image, its prompt and seed to the terminal, log file, and a Dream text chunk in the PNG metadata""" - last_seed = None - img_num = 1 - seenit = {} - - for r in results: - seed = r[1] - log_message = f'{r[0]}: {prompt} -S{seed}' - - print(log_message) - logfile.write(log_message + '\n') - logfile.flush() - +SAMPLER_CHOICES=[ + 'ddim', + 'k_dpm_2_a', + 'k_dpm_2', + 'k_euler_a', + 'k_euler', + 'k_heun', + 'k_lms', + 'plms', +] def create_argv_parser(): parser = argparse.ArgumentParser( - description="Parse script's command line args" + description="""Generate images using Stable Diffusion. + Use --web to launch the web interface. + Use --from_file to load prompts from a file path or standard input ("-"). + Otherwise you will be dropped into an interactive command prompt (type -h for help.) + Other command-line arguments are defaults that can usually be overridden + prompt the command prompt. +""" ) parser.add_argument( '--laion400m', @@ -334,51 +278,50 @@ def create_argv_parser(): '-l', dest='laion400m', action='store_true', - help='fallback to the latent diffusion (laion400m) weights and config', + help='Fallback to the latent diffusion (laion400m) weights and config', ) parser.add_argument( '--from_file', dest='infile', type=str, - help='if specified, load prompts from this file', + help='If specified, load prompts from this file', ) parser.add_argument( '-n', '--iterations', type=int, default=1, - help='number of images to generate', + help='Number of images to generate', ) parser.add_argument( '-F', '--full_precision', dest='full_precision', action='store_true', - help='use slower full precision math for calculations', + help='Use slower full precision math for calculations', ) parser.add_argument( - '--sampler', + '-g', + '--grid', + action='store_true', + help='Generate a grid instead of individual images', + ) + parser.add_argument( + '-A', '-m', + '--sampler', dest='sampler_name', - choices=[ - 'ddim', - 'k_dpm_2_a', - 'k_dpm_2', - 'k_euler_a', - 'k_euler', - 'k_heun', - 'k_lms', - 'plms', - ], + choices=SAMPLER_CHOICES, + metavar='SAMPLER_NAME', default='k_lms', - help='which sampler to use (k_lms) - can only be set on command line', + help=f'Set the initial sampler. Default: k_lms. Supported samplers: {", ".join(SAMPLER_CHOICES)}', ) parser.add_argument( '--outdir', '-o', type=str, default='outputs/img-samples', - help='directory in which to place generated images and a log of prompts and seeds (outputs/img-samples', + help='Directory to save generated images and a log of prompts and seeds. Default: outputs/img-samples', ) parser.add_argument( '--embedding_path', @@ -390,44 +333,39 @@ def create_argv_parser(): '-d', type=str, default='cuda', - help='device to run stable diffusion on. defaults to cuda `torch.cuda.current_device()` if avalible', + help='Device to run Stable Diffusion on. Defaults to cuda `torch.cuda.current_device()` if avalible', ) # GFPGAN related args - parser.add_argument( - '--gfpgan', - dest='use_gfpgan', - action='store_true', - help='load gfpgan for use in the dreambot. Note: Enabling GFPGAN will require more GPU memory', - ) - parser.add_argument( - '--gfpgan_upscale', - type=int, - default=2, - help='The final upsampling scale of the image. Default: 2. Only used if --gfpgan is specified', - ) parser.add_argument( '--gfpgan_bg_upsampler', type=str, default='realesrgan', help='Background upsampler. Default: realesrgan. Options: realesrgan, none. Only used if --gfpgan is specified', + ) parser.add_argument( '--gfpgan_bg_tile', type=int, default=400, - help='Tile size for background sampler, 0 for no tile during testing. Default: 400. Only used if --gfpgan is specified', + help='Tile size for background sampler, 0 for no tile during testing. Default: 400.', ) parser.add_argument( '--gfpgan_model_path', type=str, default='experiments/pretrained_models/GFPGANv1.3.pth', - help='indicates the path to the GFPGAN model, relative to --gfpgan_dir. Only used if --gfpgan is specified', + help='Indicates the path to the GFPGAN model, relative to --gfpgan_dir.', ) parser.add_argument( '--gfpgan_dir', type=str, default='../GFPGAN', - help='indicates the directory containing the GFPGAN code. Only used if --gfpgan is specified', + help='Indicates the directory containing the GFPGAN code.', + ) + parser.add_argument( + '--web', + dest='web', + action='store_true', + help='Start in web server mode.', ) return parser @@ -437,76 +375,108 @@ def create_cmd_parser(): description='Example: dream> a fantastic alien landscape -W1024 -H960 -s100 -n12' ) parser.add_argument('prompt') - parser.add_argument('-s', '--steps', type=int, help='number of steps') + parser.add_argument('-s', '--steps', type=int, help='Number of steps') parser.add_argument( '-S', '--seed', type=int, - help='image seed; a +ve integer, or use -1 for the previous seed, -2 for the one before that, etc', + help='Image seed; a +ve integer, or use -1 for the previous seed, -2 for the one before that, etc', ) parser.add_argument( '-n', '--iterations', type=int, default=1, - help='number of samplings to perform (slower, but will provide seeds for individual images)', + help='Number of samplings to perform (slower, but will provide seeds for individual images)', ) parser.add_argument( '-b', '--batch_size', type=int, default=1, - help='number of images to produce per sampling (will not provide seeds for individual images!)', + help='Number of images to produce per sampling (will not provide seeds for individual images!)', ) parser.add_argument( - '-W', '--width', type=int, help='image width, multiple of 64' + '-W', '--width', type=int, help='Image width, multiple of 64' ) parser.add_argument( - '-H', '--height', type=int, help='image height, multiple of 64' + '-H', '--height', type=int, help='Image height, multiple of 64' ) parser.add_argument( '-C', '--cfg_scale', default=7.5, type=float, - help='prompt configuration scale', + help='Prompt configuration scale', ) parser.add_argument( '-g', '--grid', action='store_true', help='generate a grid' ) + parser.add_argument( + '--outdir', + '-o', + type=str, + default=None, + help='Directory to save generated images and a log of prompts and seeds', + ) parser.add_argument( '-i', '--individual', action='store_true', - help='generate individual files (default)', + help='Generate individual files (default)', ) parser.add_argument( '-I', '--init_img', type=str, - help='path to input image for img2img mode (supersedes width and height)', + help='Path to input image for img2img mode (supersedes width and height)', ) parser.add_argument( '-f', '--strength', default=0.75, type=float, - help='strength for noising/unnoising. 0.0 preserves image exactly, 1.0 replaces it completely', + help='Strength for noising/unnoising. 0.0 preserves image exactly, 1.0 replaces it completely', ) parser.add_argument( '-G', '--gfpgan_strength', - default=None, + default=0, type=float, help='The strength at which to apply the GFPGAN model to the result, in order to improve faces.', ) + parser.add_argument( + '-U', + '--upscale', + nargs='+', + default=None, + type=float, + help='Scale factor (2, 4) for upscaling followed by upscaling strength (0-1.0). If strength not specified, defaults to 0.75' + ) + parser.add_argument( + '-save_orig', + '--save_original', + action='store_true', + help='Save original. Use it when upscaling to save both versions.', + ) # variants is going to be superseded by a generalized "prompt-morph" function # parser.add_argument('-v','--variants',type=int,help="in img2img mode, the first generated image will get passed back to img2img to generate the requested number of variants") parser.add_argument( '-x', '--skip_normalize', action='store_true', - help='skip subprompt weight normalization', + help='Skip subprompt weight normalization', + ) + parser.add_argument( + '-A', + '-m', + '--sampler', + dest='sampler_name', + default=None, + type=str, + choices=SAMPLER_CHOICES, + metavar='SAMPLER_NAME', + help=f'Switch to a different sampler. Supported samplers: {", ".join(SAMPLER_CHOICES)}', ) return parser diff --git a/scripts/dream_web.py b/scripts/dream_web.py deleted file mode 100644 index 227e8acdc7..0000000000 --- a/scripts/dream_web.py +++ /dev/null @@ -1,114 +0,0 @@ -import json -import base64 -import mimetypes -import os -from pytorch_lightning import logging -from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer - -print("Loading model...") -from ldm.simplet2i import T2I -model = T2I(sampler_name='k_lms') - -# to get rid of annoying warning messages from pytorch -import transformers -transformers.logging.set_verbosity_error() -logging.getLogger("pytorch_lightning").setLevel(logging.ERROR) - -print("Initializing model, be patient...") -model.load_model() - -class DreamServer(BaseHTTPRequestHandler): - def do_GET(self): - if self.path == "/": - self.send_response(200) - self.send_header("Content-type", "text/html") - self.end_headers() - with open("./static/dream_web/index.html", "rb") as content: - self.wfile.write(content.read()) - elif os.path.exists("." + self.path): - mime_type = mimetypes.guess_type(self.path)[0] - if mime_type is not None: - self.send_response(200) - self.send_header("Content-type", mime_type) - self.end_headers() - with open("." + self.path, "rb") as content: - self.wfile.write(content.read()) - else: - self.send_response(404) - else: - self.send_response(404) - - def do_POST(self): - self.send_response(200) - self.send_header("Content-type", "application/json") - self.end_headers() - - content_length = int(self.headers['Content-Length']) - post_data = json.loads(self.rfile.read(content_length)) - prompt = post_data['prompt'] - initimg = post_data['initimg'] - iterations = int(post_data['iterations']) - steps = int(post_data['steps']) - width = int(post_data['width']) - height = int(post_data['height']) - cfgscale = float(post_data['cfgscale']) - seed = None if int(post_data['seed']) == -1 else int(post_data['seed']) - - print(f"Request to generate with prompt: {prompt}") - - outputs = [] - if initimg is None: - # Run txt2img - outputs = model.txt2img(prompt, - iterations=iterations, - cfg_scale = cfgscale, - width = width, - height = height, - seed = seed, - steps = steps) - else: - # Decode initimg as base64 to temp file - with open("./img2img-tmp.png", "wb") as f: - initimg = initimg.split(",")[1] # Ignore mime type - f.write(base64.b64decode(initimg)) - - # Run img2img - outputs = model.img2img(prompt, - init_img = "./img2img-tmp.png", - iterations = iterations, - cfg_scale = cfgscale, - seed = seed, - steps = steps) - # Remove the temp file - os.remove("./img2img-tmp.png") - - print(f"Prompt generated with output: {outputs}") - - post_data['initimg'] = '' # Don't send init image back - - # Append post_data to log - with open("./outputs/img-samples/dream_web_log.txt", "a") as log: - for output in outputs: - log.write(f"{output[0]}: {json.dumps(post_data)}\n") - - outputs = [x + [post_data] for x in outputs] # Append config to each output - result = {'outputs': outputs} - self.wfile.write(bytes(json.dumps(result), "utf-8")) - -if __name__ == "__main__": - # Change working directory to the stable-diffusion directory - os.chdir( - os.path.abspath(os.path.join(os.path.dirname( __file__ ), '..')) - ) - - # Start server - dream_server = ThreadingHTTPServer(("0.0.0.0", 9090), DreamServer) - print("\n\n* Started Stable Diffusion dream server! Point your browser at http://localhost:9090 or use the host's DNS name or IP address. *") - - try: - dream_server.serve_forever() - except KeyboardInterrupt: - pass - - dream_server.server_close() - diff --git a/scripts/preload_models.py b/scripts/preload_models.py index 624b61e48e..ba7b242ece 100755 --- a/scripts/preload_models.py +++ b/scripts/preload_models.py @@ -3,6 +3,9 @@ # Before running stable-diffusion on an internet-isolated machine, # run this script from one with internet connectivity. The # two machines must share a common .cache directory. +from transformers import CLIPTokenizer, CLIPTextModel +import clip +from transformers import BertTokenizerFast import sys import transformers import os @@ -12,7 +15,6 @@ transformers.logging.set_verbosity_error() # this will preload the Bert tokenizer fles print('preloading bert tokenizer...') -from transformers import BertTokenizerFast tokenizer = BertTokenizerFast.from_pretrained('bert-base-uncased') print('...success') @@ -28,8 +30,6 @@ version = 'openai/clip-vit-large-patch14' print('preloading CLIP model (Ignore the deprecation warnings)...') sys.stdout.flush() -import clip -from transformers import CLIPTokenizer, CLIPTextModel tokenizer = CLIPTokenizer.from_pretrained(version) transformer = CLIPTextModel.from_pretrained(version) @@ -63,6 +63,20 @@ if gfpgan: scale=2, ), ) + + RealESRGANer( + scale=4, + model_path='https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth', + model=RRDBNet( + num_in_ch=3, + num_out_ch=3, + num_feat=64, + num_block=23, + num_grow_ch=32, + scale=4, + ), + ) + FaceRestoreHelper(1, det_model='retinaface_resnet50') print('...success') except Exception: diff --git a/static/colab_notebook.png b/static/colab_notebook.png new file mode 100644 index 0000000000..933664a86f Binary files /dev/null and b/static/colab_notebook.png differ diff --git a/static/dream_web/index.css b/static/dream_web/index.css index ed840a056a..8b0f4785f7 100644 --- a/static/dream_web/index.css +++ b/static/dream_web/index.css @@ -1,61 +1,69 @@ -* { - font-family: 'Arial'; -} -#header { - text-decoration: dotted underline; -} -#search { - margin-top: 20vh; - margin-left: auto; - margin-right: auto; - max-width: 800px; - - text-align: center; -} -fieldset { - border: none; -} -#fieldset-search { - display: flex; -} -#prompt { - flex-grow: 1; - - border-radius: 20px 0px 0px 20px; - padding: 5px 10px 5px 10px; - border: 1px solid black; - border-right: none; - outline: none; -} -#submit { - border-radius: 0px 20px 20px 0px; - padding: 5px 10px 5px 10px; - border: 1px solid black; -} -#results { - text-align: center; - max-width: 1000px; - margin: auto; - padding-top: 10px; -} -img { - cursor: pointer; - height: 30vh; - border-radius: 5px; - margin: 10px; -} -#fieldset-config { - line-height:2em; -} -input[type="number"] { - width: 60px; -} -#seed { - width: 150px; -} -hr { - width: 200px; -} -label { - white-space: nowrap; -} +* { + font-family: 'Arial'; +} +#header { + text-decoration: dotted underline; +} +#search { + margin-top: 20vh; + margin-left: auto; + margin-right: auto; + max-width: 800px; + + text-align: center; +} +fieldset { + border: none; +} +#fieldset-search { + display: flex; +} +#scaling-inprocess-message{ + font-weight: bold; + font-style: italic; + display: none; +} +#prompt { + flex-grow: 1; + + border-radius: 20px 0px 0px 20px; + padding: 5px 10px 5px 10px; + border: 1px solid black; + border-right: none; + outline: none; +} +#submit { + border-radius: 0px 20px 20px 0px; + padding: 5px 10px 5px 10px; + border: 1px solid black; +} +#reset-all { + background-color: pink; +} +#results { + text-align: center; + max-width: 1000px; + margin: auto; + padding-top: 10px; +} +img { + cursor: pointer; + height: 30vh; + border-radius: 5px; + margin: 10px; +} +#fieldset-config { + line-height:2em; +} +input[type="number"] { + width: 60px; +} +#seed { + width: 150px; +} +hr { + width: 200px; +} +label { + white-space: nowrap; +} diff --git a/static/dream_web/index.html b/static/dream_web/index.html index 4dccd05fb3..34ee69bad2 100644 --- a/static/dream_web/index.html +++ b/static/dream_web/index.html @@ -1,66 +1,94 @@ - - - Stable Diffusion Dream Server - - - - - - - - -
-
-
-

No results...

 -
-
- - + + + Stable Diffusion Dream Server + + + + + + + + +
+
+

No results...

 +
+
+ + diff --git a/static/dream_web/index.js b/static/dream_web/index.js index 3b99deecf4..ec9626f327 100644 --- a/static/dream_web/index.js +++ b/static/dream_web/index.js @@ -1,101 +1,129 @@ -function toBase64(file) { - return new Promise((resolve, reject) => { - const r = new FileReader(); - r.readAsDataURL(file); - r.onload = () => resolve(r.result); - r.onerror = (error) => reject(error); - }); -} - -function appendOutput(output) { - let outputNode = document.createElement("img"); - outputNode.src = output[0]; - - let outputConfig = output[2]; - let altText = output[1].toString() + " | " + outputConfig.prompt; - outputNode.alt = altText; - outputNode.title = altText; - - // Reload image config - outputNode.addEventListener('click', () => { - let form = document.querySelector("#generate-form"); - for (const [k, v] of new FormData(form)) { - form.querySelector(`*[name=${k}]`).value = outputConfig[k]; - } - document.querySelector("#seed").value = output[1]; - - saveFields(document.querySelector("#generate-form")); - }); - - document.querySelector("#results").prepend(outputNode); -} - -function appendOutputs(outputs) { - for (const output of outputs) { - appendOutput(output); - } -} - -function saveFields(form) { - for (const [k, v] of new FormData(form)) { - if (typeof v !== 'object') { // Don't save 'file' type - localStorage.setItem(k, v); - } - } -} -function loadFields(form) { - for (const [k, v] of new FormData(form)) { - const item = localStorage.getItem(k); - if (item != null) { - form.querySelector(`*[name=${k}]`).value = item; - } - } -} - -async function generateSubmit(form) { - const prompt = document.querySelector("#prompt").value; - - // Convert file data to base64 - let formData = Object.fromEntries(new FormData(form)); - formData.initimg = formData.initimg.name !== '' ? await toBase64(formData.initimg) : null; - - // Post as JSON - fetch(form.action, { - method: form.method, - body: JSON.stringify(formData), - }).then(async (result) => { - let data = await result.json(); - - // Re-enable form, remove no-results-message - form.querySelector('fieldset').removeAttribute('disabled'); - document.querySelector("#prompt").value = prompt; - - if (data.outputs.length != 0) { - document.querySelector("#no-results-message")?.remove(); - appendOutputs(data.outputs); - } else { - alert("Error occurred while generating."); - } - }); - - // Disable form while generating - form.querySelector('fieldset').setAttribute('disabled',''); - document.querySelector("#prompt").value = `Generating: "${prompt}"`; -} - -window.onload = () => { - document.querySelector("#generate-form").addEventListener('submit', (e) => { - e.preventDefault(); - const form = e.target; - - generateSubmit(form); - }); - document.querySelector("#generate-form").addEventListener('change', (e) => { - saveFields(e.target.form); - }); - document.querySelector("#reset").addEventListener('click', (e) => { - document.querySelector("#seed").value = -1; - saveFields(e.target.form); - }); - loadFields(document.querySelector("#generate-form")); -}; +function toBase64(file) { + return new Promise((resolve, reject) => { + const r = new FileReader(); + r.readAsDataURL(file); + r.onload = () => resolve(r.result); + r.onerror = (error) => reject(error); + }); +} + +function appendOutput(src, seed, config) { + let outputNode = document.createElement("img"); + outputNode.src = src; + + let altText = seed.toString() + " | " + config.prompt; + outputNode.alt = altText; + outputNode.title = altText; + + // Reload image config + outputNode.addEventListener('click', () => { + let form = document.querySelector("#generate-form"); + for (const [k, v] of new FormData(form)) { + form.querySelector(`*[name=${k}]`).value = config[k]; + } + document.querySelector("#seed").value = seed; + + saveFields(document.querySelector("#generate-form")); + }); + + document.querySelector("#results").prepend(outputNode); +} + +function saveFields(form) { + for (const [k, v] of new FormData(form)) { + if (typeof v !== 'object') { // Don't save 'file' type + localStorage.setItem(k, v); + } + } +} + +function loadFields(form) { + for (const [k, v] of new FormData(form)) { + const item = localStorage.getItem(k); + if (item != null) { + form.querySelector(`*[name=${k}]`).value = item; + } + } +} + +function clearFields(form) { + localStorage.clear(); + let prompt = form.prompt.value; + form.reset(); + form.prompt.value = prompt; +} + +async function generateSubmit(form) { + const prompt = document.querySelector("#prompt").value; + + // Convert file data to base64 + let formData = Object.fromEntries(new FormData(form)); + formData.initimg = formData.initimg.name !== '' ? await toBase64(formData.initimg) : null; + + document.querySelector('progress').setAttribute('max', formData.steps); + + // Post as JSON, using Fetch streaming to get results + fetch(form.action, { + method: form.method, + body: JSON.stringify(formData), + }).then(async (response) => { + const reader = response.body.getReader(); + + let noOutputs = true; + while (true) { + let {value, done} = await reader.read(); + value = new TextDecoder().decode(value); + if (done) break; + + for (let event of value.split('\n').filter(e => e !== '')) { + const data = JSON.parse(event); + + if (data.event == 'result') { + noOutputs = false; + document.querySelector("#no-results-message")?.remove(); + appendOutput(data.files[0],data.files[1],data.config) + } else if (data.event == 'upscaling-started') { + document.getElementById("processing_cnt").textContent=data.processed_file_cnt; + document.getElementById("scaling-inprocess-message").style.display = "block"; + } else if (data.event == 'upscaling-done') { + document.getElementById("scaling-inprocess-message").style.display = "none"; + } else if (data.event == 'step') { + document.querySelector('progress').setAttribute('value', data.step.toString()); + } + } + } + + // Re-enable form, remove no-results-message + form.querySelector('fieldset').removeAttribute('disabled'); + document.querySelector("#prompt").value = prompt; + document.querySelector('progress').setAttribute('value', '0'); + + if (noOutputs) { + alert("Error occurred while generating."); + } + }); + + // Disable form while generating + form.querySelector('fieldset').setAttribute('disabled',''); + document.querySelector("#prompt").value = `Generating: "${prompt}"`; +} + +window.onload = () => { + document.querySelector("#generate-form").addEventListener('submit', (e) => { + e.preventDefault(); + const form = e.target; + + generateSubmit(form); + }); + document.querySelector("#generate-form").addEventListener('change', (e) => { + saveFields(e.target.form); + }); + document.querySelector("#reset-seed").addEventListener('click', (e) => { + document.querySelector("#seed").value = -1; + saveFields(e.target.form); + }); + document.querySelector("#reset-all").addEventListener('click', (e) => { + clearFields(e.target.form); + }); + loadFields(document.querySelector("#generate-form")); +};