tutorials

CommunityDocs/Sources/CommunityDocs/CommuntyDocs.docc/1.UI.md

@@ -0,0 +1,78 @@
+# Drawthings Tutorials - Basic UI
+
+
+## First section is about UI of Draw Things app
+
+F_R_O_S_T_Y
+
+
+
+![First section is about UI of Draw Things app](https://cdn.discordapp.com/attachments/1058172691309404170/1159101377520341042/IMG_0254.jpg?ex=660d4847&is=65fad347&hm=97d9205ef9fd6d7c203ab254a4f60c096b98e58ca8b3dc5eb0dd4c72c7fccb0b&)
+
+1 - Configuration - Here you can save your configuration as template, it will save all the settings below this. You can save as many templates as you want and switch between them and share them as well. 
+
+2 - Prompt windows - Here you can type your prompt. When you first open the app, it will be filled with random prompt. You can try it and generate picture. Beside is window for negative prompt. It serves for what you don’t want to see on the generated picture. For iPhone, you must swipe the prompt window to the left to see negative prompt window, watch the arrow beside the prompt window.
+
+3 - Prompt slider  - Move this to go past in history of prompts. 
+
+4 - Generate - When you click it, it will generate image with all the settings and prompts. For iPhone, long hold to generate up to 10 images after each other.
+
+5 - Some as 4 for iPhone, here you can select up to 100 images to generate after each other. 
+
+6 - Layers  - Click this will open list of all supported layers. When you select any controlNET  from control settings, under it you will see input and beside which layers the selected controlNET using. Pose  layer can extract pose from real picture. Depth map  can extract depth from portrait photos from your iPhone. It support open poses skeletons and depth map images. 
+
+7 - Zoom  - Here you can choose zoom in your canvas. Or you can zoom in/out manually with gestures like on your iPhone in photos. 
+
+8 - Presets  - Here you can quickly start upscale or face restoration after you downloaded their model from settings section. Or use custom scripts (find them on Discord or make your own when you understand what you are doing). 
+
+9 - Project  - Here you can start new project, load old ones or rename them. They are stored in files app, local, draw things. After long usage, these files will be big, so clean them manually to save space.
+If you want to clean project files to save space, jump here to find how 
+
+
+## [old version]First section will be all about UI of Draw Things app
+
+
+![First section is about UI of Draw Things app](https://cdn.discordapp.com/attachments/1058172691309404170/1058175920176898098/IMG_8831.png?ex=6606079f&is=65f3929f&hm=2a12d7fd47c5e3d94b0483cf1dd55435d60a97d0ba25aed06f725b1b654d6946&)
+
+This is basic tutorial explaining UI of Draw Things app with some tips. The app is under active development so expect some things can change in future and other can be added. Experiment with the settings and tools! You cannot do anything wrong.  For prompt inspiration check internet, for example (https://lexica.art/). 
+
+Prompt window - if you slide it to the left, you will see window for negative prompt. In prompt, you can use (something) to emphasize the text, make it more important. If you use [something], you will de-emphasize and make it less important. You can multiple it by adding more (((something))) or write (something:2). 
+
+1 - This button will let you start a new project, it’s mean it will reset all your prompt history and all your picture history, other settings will stay untouched. Now you can rename your project, load your old project or export it. 
+
+2 - This menu will let you quickly set strength in 10% increments. You can find description about strength in settings (5). In short, 100% will generate totally new image, 0% change nothing. Changing this is most important for img2img or inpainting.
+
+3 - Seed number. Find description in settings (5). If click the button, it will generate new random number. If you long press/right click it, it will select the numbers and you can manually change number or paste number you already copied before.
+
+4 - In this menu you can change resolution of your image. For most models 512x512 is best one. Some models like Generic HD (Stable diffusion 2.0 768-v) are best with 768x768. If you generate in different resolutions then recommended for selected model (every model is trained for some selected resolutions), you can expect some problems like duplication, bad generated images, etc.
+
+5 - Settings button. Inside you can set everything for the app and read a lot of description about functions. 
+
+6 - Save button. If you click it, it will automatically save current generated picture in your photos. If you long press/right click it, it will let you choose where you want to save the picture.
+
+7 - Share button, same like share button in iOS. Airdrop, share to other apps etc.
+
+8 - This button will select all text in your prompt window, so you can easily replace it, delete it… It will save you few clicks.
+If the words get orange color, it’s signaling it’s more then 75 words, it was prompt limit before and now it’s mean the orange words can be on the image or not, because the prompt is too long. 
+
+9 - Cog button, now you can easily start script (predefined settings) with one click. Later this menu will be customizable, so you can set your own settings and with one click generate picture with that settings.
+
+10 - Generate button, when you click it, it will generate picture with your prompt and all what is set in your settings (5). When you will long press, it will let you generate more images (batch generating), all settings will be same, only seed will be different for each picture. First one will generate image with seed you see in seed (3), other will be random. Also, it is deterministic for batch generation. From the same first-image seed, you will also end up with the same second-image - n-th image seeds. So don’t forget to click seed button, or the first image will be same like your last one if you already generate one. 
+11 - Prompt history slider. If you will move the slider to the left, you will go back in history of all your prompt changes.
+
+12 - Picture history slider, if you will move the slider to the left, you will go back in history of all your images you generate, including all your changes in pictures you generate, like using magic wand (13) eraser (15) brush (16) etc. 
+
+13 - Magic wand, if selected, it will let you quickly select objects, like person, or some object of similar color. After you can use eraser (15) brush (16) in that marked areas. Sometimes it can be inaccurate. 
+
+14 - Hand, if you select this tool, you can move the picture in picture window. Useful for example if you generate square 512x512 portrait picture with person and you want to generate bottom of the person body, you can select 512x768 resolution first and after select hand tool and move generated picture up, select inpainting model and click generate, it will try to fill the bottom empty place. If you hold generate button (10) you can select more pictures and you will get more variations. After you can use picture history slider (12) and check quickly which one you like. 
+
+15 - Eraser tool. When you already import or generate image and you want to change some part of the image, you can use this tool for inpainting. When you hold the button, you can use this tool for cleaning what you erase before. Select area, select inpainting model, change your prompt and hit generate. Don’t forget what is write about strength above in this tutorial. Long press/right click change eraser to clean already masked area.
+
+16 - Brush tool. You can draw something in the picture area, for example sketch tree, mountain and person. After write in your prompt “person staying in front of mountain beside tree” and if you will be lucky, generated picture will place the objects where you sketch them. When you will long press/right click the button, you can select colors. 
+
+17 - New canvas button (before Trash button), let you only clean the canvas window. Even you clean it, you can find pictures you clean under history button (19) or picture history slider (12). Is not delete button from history. 
+
+18 - Camera button, if you click it, it will let you choose picture to import from your gallery. If you long press/right click it, it will let you paste image you copy to clipboard before or work with masking/depth map. If you want insert non square image, don’t forget to change resolution (4) first to match the aspect ratio of imported image. 
+
+19 - History. It will show you all history of your generated images and all changes you do for them with other tools. When long press/right click on picture here, you can delete that picture from history. There are the buttons, from left whole history with all edits, middle is tree history showing history from last editing and generation and coffee button for show only generated images. 
+

CommunityDocs/Sources/CommunityDocs/CommuntyDocs.docc/2.Models.md

@@ -0,0 +1,70 @@
+# Drawthings Tutorials - Models
+
+
+## Models importing/deleting/mixing
+
+F_R_O_S_T_Y
+
+
+When you click the model menu, you will find list of prepared models. They are functional and already prepared for usage. Always let the app download all the files(don’t close the app to the background on iOS), or it can cause problems. Models can be between 800MB for 8-bit models, 1,8GB for normal 1.5 models to almost 10GB for SDXL model. 
+
+When you click Manage  new window will open and you will see list of models for download/delete, three dots for export and create 8-bit model. In this window you can select external folder for your models. 
+
+At the bottom, next icon is Import model , where you can manually import models. Read the description carefully . You can download models for example from civitai website or use the green play button beside download model, where you select draw things and it will open this import model window automatically and prefill some settings. If the model have external VAE(it is not baked inside the model already), don’t forget to download it first, after insert the model for import and insert the downloaded VAE and after click import. 
+
+Last right button is about Model mixing . Here you can mix more models together and create your own mix.
+
+Weighted sum: you select two or more models and combine them together, like Model 1 Generic 1.5 model, model 2 Anything V3. For generic you will choose 0,3, Anything will be set automatically to 0,7. This mean final model will be 30% from generic and 70% from Anything. 
+Add difference: when you want to make quick inpainting model from other models, Model 1 must be inpainting model 1.5 (because you will add difference in this model). Model 2 will be the model you want to add inside inpainting, so for example Anything V3. For Model 3 is important to find base model. It must be the model Model 2 is based (civitai showing this information for most models here in description). So anything is based on model generic 1.5, so Model 3 must be generic 1.5. Now you can experiment for best results, try to set 0,8 for Model 2 and try it. If you don’t like the results, try lower or rise the number and try again.
+
+
+## [old version]Models importing
+
+![model](https://cdn.discordapp.com/attachments/1058172691309404170/1059117752079630346/IMG_8945.jpg?ex=660974c5&is=65f6ffc5&hm=4bff53bd3acbab8da95800b8a6d449b196ac14fefd394737c803c8c910771403&)
+
+For Lora models, process is almost same, but you import it under Lora models list, not under normal model list. If you want import your own model which is not in model list(there are already models for pix2pix, depth2img, inpainting etc., so you don’t need to import them, choose from the in app list), you must click settings button, after model menu (1), select Customize (2) and here it’s important to read descriptions of all settings. 
+There are three ways how to import custom model. First you need to find website providing them like (https://civitai.com/) or (https://huggingface.co/) or many others. 
+
+After you can choose how to import model in Draw Things. 
+
+![import](https://cdn.discordapp.com/attachments/1058172691309404170/1059118667721347113/IMG_8946.jpg?ex=6609759f&is=65f7009f&hm=9ae2de67300736500bbd555b363de23a02aa2e743bc4a8db63287d00abf050c9&)
+
+First way is from (https://civitai.com/) there is official support for importing models to Draw Things. If you click the green play button you can directly import it inside Draw Things app. It will open Draw things app with dialog to download it. 
+
+Second way is download the model, above you can see how it looks (1) and (👍). You need to see the window for download (2). This is important! If you click download, the file will download inside Files app (or the folder in your macOS where you normally download files from internet). Here, after download you need to move the files inside My phone/Draw Things/Downloads as you can see above. For Mac Downloads folder is there:
+
+###Directory of DT for macOS  
+
+/Users/yourusername/Library/Containers/com.liuliu.draw-things/Data
+or
+user/Library/Containers/Draw Things/Data/Documents/Models
+maybe you need to enable viewing hidden folders with cmd+shift+.
+or
+you can directly put it under ~/Downloads of your home directory, it will first ask for permission and then you can import the model. 
+
+Third is copy link and insert it to Draw Things model import. Process is similar, but you don’t click Download, however you need to copy the link in your clipboard. As you can see above, if you copy link for model from (❌) it won’t work, because you copy link of website only! Every time make sure you copy link from (1) or (👍).
+
+It’s easy, when you click some link and it ask you if you want to download it, you can copy same link in your clipboard and paste it in Draw Things. 
+
+Draw Things will download the model from link and after you can import it. 
+
+After successful import, Draw Things will ask you if you want to delete the downloaded model (not the imported), if you click yes, it will clean Downloads folder for you, so you don’t need to go here and manually delete the downloaded model.
+
+###Changing model name and some details after importing
+
+You can download some app for editing, for example Documents by Readdle and go to DT folder, models and here you can find custom.json file. If you look inside, you will see descriptions about models you imported. So if you feel like expert, you can edit them. But for your safety, backup the original file first before editing. 
+
+And small tip if you want to save space. As you can see above in picture from Files app, there is lot of untitled SQLite files. They are created every time you click Start a new project. It’s history files and if you don’t plan to use them, you can delete them all to save space. 
+
+
+###Deleting models
+
+If you want to delete models, soon there will be way to delete them from Draw Things app. Now you must visit Files app as you can see in picture above, My phone/Draw Things/Models and here you can delete them. You can sort the files inside Models folder by time when you click the three dots in right top corner. Every model have 2 or more files, one will be under 2 GB and other somewhere around 500 MB. You can delete the pairs and when you will start Draw Things the deleted model won’t show in model list. 
+
+###Model mixing tutorial
+
+If you want to mix models, you must go to settings, open menu for models and click the first button “Customize”. At the bottom you can see two buttons, if you select right one, you will enter the model mixing screen. 
+
+Weighted sum: you select two or more models and combine them together, like Model 1 Generic 1.5 model, model 2 Anything V3. For generic you will choose 0,3, Anything will be set automatically to 0,7. Is mean final model will be 30% from generic and 70% from Anything. 
+
+Add difference: when you want to make quick inpainting model from other models, Model 1 must be inpainting model 1.5 (because you will add difference in this model). Model 2 will be the model you want to add inside inpainting, so for example Anything V3. For Model 3 is important to find base model. It must be the model Model 2 is based (civitai showing this information for most models here in description). So anything is based on model generic 1.5, so Model 3 must be generic 1.5. Now you can experiment for best results, try to set 0,8 for Model 2 and try it. If you don’t like the results, try lower or rise the number and try again. 

CommunityDocs/Sources/CommunityDocs/CommuntyDocs.docc/3.LoRa.md

@@ -0,0 +1,20 @@
+# Drawthings Tutorials - Lora
+
+
+## Everything about Lora and training your own Lora model
+
+F_R_O_S_T_Y
+
+
+Limitation now is minimum of iPad with 8GB of RAM for 1.5 models Lora, use 8 bit models  and network dim not higher then default. iPhone 15 PRO models can crash when training, but you can try it with 8 bit model and network dim set to 8. For SDXL Lora  you will need powerful hardware with lot of RAM.
+
+For everyone interested in Lora training, you can find some more info in ⁠🚝training-recipes-and-results 
+Click the menu beside Lora in settings and here you can download premade Lora. When you click manage  you will be in list of all Lora. You can download/delete them from here. Click to three dots to export/create 8- bit model. 
+
+Second menu in the middle is import Lora . Same as model importing, you can select local file or import directly from civitai with the small green play button beside download and select draw things. Don’t forget to fill trigger word . This word will be added to the prompt. This word will trigger the Lora. And when you select Lora, under the menu will be slider to select Lora strength. You can select multiple Lora by click the plus button beside the selected Lora. 
+
+Last button is for Lora training. Here you can train your own Lora. Don’t forget to read all description here again . For base model you can select base 1.5 or realistic vision for realistic photos, anything for anime pictures etc. Depends what look or style you want to achieve. Trigger word  is the special word that trigger the Lora. It must be unique, don’t use word like “Bieber””, or it will mix your Lora with the singer photos. Other you can leave default until you get some experience. Training Steps, you can lower to 500-1000 for start and see the results. When you use lot of steps or high learning rate, you will overcook your model and it will generate burned pictures or noise only.  When you prefill the auto fill prompt before importing photos, the text here will fill all the imported photos. You can do good Lora with only 10 or 15 photos of the character or style. Don’t need hundreds. Better few good photos, then hundred of bad quality. Experiment or try other users settings.
+
+You can also check YouTube tutorials about Lora training, you will find lot of them and get experience about how to train good Lora, most of the parameters are similar here like in automatic kohya-ss
+
+

CommunityDocs/Sources/CommunityDocs/CommuntyDocs.docc/4.ControlNET.md

@@ -0,0 +1,21 @@
+# Drawthings Tutorials - ControlNET
+
+
+## Everything about ControlNET
+
+F_R_O_S_T_Y
+
+Another menu in settings is for control. Inside you can select control you want to use. When you select any control from the list, under it will appear input  and here you will find what layers the controlNET using. If you want to find more about different controlNET, use Google.  Or check the old tutorial section, here you can find few links. 
+
+In manage  menu, you can download/delete controlNET or import other one. Importing SDXL controlNET is not supported right now. 
+
+You can combine different controlNET together like Lora by click plus button beside the controlNET menu and add another one. 
+
+
+### ControlNET introduction
+
+You can find controlNET under settings as Control. Read the announcement bellow for more details. Below you can find two links (not because I’m lazy, but clever people then me already wrote some tutorials). Civitai link showing how the models working for reference, you don’t need to download the models here (not all of them must be available in DT) and Github link is for more technical description. 
+
+https://civitai.com/models/9868/controlnet-pre-trained-difference-models
+
+https://github.com/lllyasviel/ControlNet/blob/main/README.md