skquark / ai-friends

A collection of handy helpers for AI art generation, AI writing and other experimental tools

AI-Friends

A collection of handy helpers for AI art generation, AI writing and other experimental tools

🎨 Stable Diffusion Deluxe Edition 👨‍🎨️ - Python to Flutter Framework

...using 🧨diffusers and practical bonus features...

---

Designed by Skquark, Inc. 😋 - Project at DiffusionDeluxe.com

• Runs in a pretty WebUI using Flet - Flutter for Python with themes, interactivity & sound
• Saves all settings/parameters in your config file, don't need to Copy to Drive
• Run a batch list of prompts at once, so queue many and walk away
• Option to override any parameter per prompt in queue
• Option to use Stability-API tokens for more samplers, bigger size & CPU runtime
• Use Stable Diffusion XL, 2.1, 2.0, 1.5 , or 1.4 Checkpoint Model File
• Supports Stable Diffusion image2image to use an init_image
• Supports Stable Diffusion Inpaint mask_image layer
• Supports Negative Prompts to specify what you don't want
• Supports Long Prompt Weighting to emphasize (positive) & [negative] word strengths
• Prompt tweening to combine latent space of 2 prompts in a series
• Can use Interpolation to walk steps between latent space of prompt list
• Can use CLIP Guidance with LAION & OpenAI ViT models
• Can use Textual Inversion Conceptualizer with 760+ Community Concepts
• Can Centipede prompts as init images feeding down the list
• Can save all images to your Google Drive (PyDrive support soon)
• Can Upscale automatically with Real-ESRGAN enlarging
• Embeds exif metadata directly into png files
• Disabled NSFW filtering and added custom sampler options
• Renames image filenames to the prompt text, with options
• OpenAI Prompt Generator, Remixer, Brainstormer & Noodle Soup Prompt Writer included
• Standalone ESRGAN Upscaler for batch uploads and image splitting
• Experimental HarmonAI Dance Diffusion audio generator
• Experimental DreamFusion 3D model generator with texture & video
• Additional features added regularly...

Can also use origional Colab implementation of Enhanced Stable Diffusion instead..

Try these other useful notebooks Enhanced DiscoArt and Structured Prompt Generator

Feature Short List: Uses Enhanced Diffusers in Material UI Flutter/Flet GUI with Themes & SoundFX, Stable Diffusion XL & lower, advanced Prompts List with overrides, many Finetuned Community Models, Dreambooth Library, Long Prompt Weighting, Walk Interpolation, Prompt Tweening, Centipede Prompts as init-images, CLIP-Guided, Textual-Inversion Conceptualizer, Dual Guided Versatile Diffusion, Image Variation, LoRA Adapters, IP-Adapters, iMagic, Depth2Image, Composable, Self-Attention Guidance, Attend & Excite, Panorama, Safe Pipeline, ControlNet SDXL & XS, DeepFloyd-IF, Stable Cascade, Wuerstchen, PixArt-alpha, LMD+, LCM, unCLIP Generator, unCLIP Image Variations, unCLIP Interpolation & Image Interpolation, LEdits++, Null-Text Inversion, AnyText, aMUSEd, DemoFusion, Text-to-Video, Text2Video-Zero, AnimateDiff Enhanced, SVD, Potat1 Text-to-Video, Infinite Zoom, Rerender-a-Video, TemporalNet XL, ControlNet Video2Video, Video-to-Video, ROOP Face Swapper, Video ReTalking, AnimateDiff to-Video, I2VGen-XL, Stable Animation, Stability-API, PIA Image Animator, TokenFlow, StyleCrafter, RAVE, AIHorde-API, SD2 4X Upscale, Real-ESRGAN Upscaling, Prompt Writer, PaLM Gemini, Antrhopic Claude 3, GPT-3, 4 ChatGPT Prompt Generator, Prompt Remixer, Prompt Brainstormer, Styler, Negatives Builder, GPT-2 Magic Prompt, Distil GPT-2, DreamBooth, LoRA & Texual Inversion Trainer, Model Converter & Merger, SD2 Image Variations, EDICT Editor, DiffEdit, MagicMix, RePainter, Paint-by-Example, Instruct Pix2Pix, ControlNet Multi, ControlNet QRCode, BLIP-Diffusion, Reference-Only, Re-Segment Anything, CLIP-Styler, Semantic Guidance, Material Diffusion, DreamFusion 3D, Point-E 3D, Shap-E 3D, LDM3D, Luma Vid-to-3D, ZoeDepth, MarigoldDepth, Tripo, CRM 3D, InstantNGR, Meshy.ai, Tortoise TTS, HarmonAI Dance Diffusion, Audio Diffusion, Bark, Riffusion, AudioLDM Text2Sound, MusicLDM, MusicGen, ZETA Editing, Mubert Music, Whisper STT, VoiceFixer, Image2Text Interrogator, DALL-E 2 API, DALL-E 3, Kandinsky 3/2.2 & Fuser, Kandinsky ControlNet, DeepDaze, Background Remover, Metadata in png, smart filenames, Batch Upscaler, Prompt Retriever, Cache Manager, Init Images from Folder or Video, and more being added regularly..

ai-friends's Issues

First few attemps

Mobile user here.

I may be doing the setup wrong. Followed instructions best I could. Artist here amateur dabbling in code.

The last instruction I have circled evades my comprehension.

Also, when I place json in project directory I get this error.

Was however able to get the local tunnel/ app up, but when I hit install nothing happens. More to come if more info is needed.

Thank you for your work

AnimateDiff Improved + controlnet

Theres a new Fork to For animateDiff that uses the same animatediff you implement..but adds the ability to make things longer and use controlnet for better control, https://github.com/s9roll7/animatediff-cli-prompt-travel
Plus there's a discord of some of the people trying to train the motion modules for animatediff if you like to implement some of the work they are doing here's the discord https://discord.gg/m9arRBBf

Tried to run it, it said python3 not recognized and shut off?

not sure how to fix it, since my python is properly installed to path

Any Chance of New NeRF method implementation?

was wondering if you are considering on adding
https://github.com/graphdeco-inria/gaussian-splatting
for training and viewing since NeRF never really have any good GUI going for them and the setup process is Hell...
but this new Gaussian Splatting brings a lot of quality in realtime..
So just wondering if you were considering add this?

Desktop Error : AnimateDiff Broken.

tried to generate a vid, i didnt use any controlnet parameters

Cloning into 'animatediff-cli-prompt-travel'...
remote: Enumerating objects: 870, done.
remote: Counting objects: 100% (299/299), done.
remote: Compressing objects: 100% (65/65), done.
remote: Total 870 (delta 264), reused 240 (delta 232), pack-reused 571
Receiving objects: 100% (870/870), 1.84 MiB | 2.39 MiB/s, done.
Resolving deltas: 100% (521/521), done.
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
ERROR: Could not install packages due to an OSError: [WinError 5] Access is denied: 'C:\Program Files (x86)\StableDiffusionDeluxe\venv\Lib\site-packages\cv2\cv2.pyd'
Check the permissions.

WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\program files (x86)\stablediffusiondeluxe\venv\lib\site-packages)
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
copier 8.2.0 requires pydantic>=2.0.3, but you have pydantic 1.10.12 which is incompatible.
Exception in thread Thread-409 ():
Traceback (most recent call last):
File "C:\Users\mahmo\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrap_inner
self.run()
File "C:\Users\mahmo\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "C:\Program Files (x86)\StableDiffusionDeluxe\venv\Stable-Diffusion-Deluxe.py", line 9737, in
ElevatedButton(content=Text("💚 Run AnimateDiff", size=20), color=colors.ON_PRIMARY_CONTAINER, bgcolor=colors.PRIMARY_CONTAINER, height=45, on_click=lambda _: run_animate_diff(page)),
File "C:\Program Files (x86)\StableDiffusionDeluxe\venv\Stable-Diffusion-Deluxe.py", line 30968, in run_animate_diff
run_sp(f"rm -rf {sd_models}", realtime=False)
File "C:\Program Files (x86)\StableDiffusionDeluxe\venv\Stable-Diffusion-Deluxe.py", line 51, in run_sp
return subprocess.run(cmd_list, stdout=subprocess.PIPE, env=env).stdout.decode('utf-8')
File "C:\Users\mahmo\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 501, in run
with Popen(*popenargs, **kwargs) as process:
File "C:\Users\mahmo\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 969, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Users\mahmo\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 1438, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
FileNotFoundError: [WinError 2] The system cannot find the file specified

Issue with Donwloading the model and running generate?

It took awhile to download the model, and I'm not even sure where it downloaded.. i think u need to add a button to show where the download folder is, to make sure it did download or not or for sure. And i think you should add the ability for people to find their already downloaded safetensor models, and convert them to diffusers

this is the error i got, after 1.5 supposedly downloaded and me trying to generate a normal image:

C:\Program Files (x86)\StableDiffusionDeluxe\venv\lib\site-packages\setuptools\installer.py:27: SetuptoolsDeprecationWarning: setuptools.installer is deprecated. Requirements should be satisfied by a PEP 517 installer.
warnings.warn(
C:\Program Files (x86)\StableDiffusionDeluxe\venv\lib\site-packages\setuptools\command\easy_install.py:144: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
warnings.warn(
C:\Program Files (x86)\StableDiffusionDeluxe\venv\lib\site-packages\setuptools\command\install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
warnings.warn(
Exception in thread Thread-244 (run_diffusion):
Traceback (most recent call last):
File "C:\Users\mahmo\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrap_inner
self.run()
File "C:\Users\mahmo\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "C:\Program Files (x86)\StableDiffusionDeluxe\venv\Stable-Diffusion-Deluxe.py", line 2701, in run_diffusion
start_diffusion(page)
File "C:\Program Files (x86)\StableDiffusionDeluxe\venv\Stable-Diffusion-Deluxe.py", line 16571, in start_diffusion
generator = torch.Generator("cuda").manual_seed(rand_seed)
RuntimeError: Device type CUDA is not supported for torch.Generator() api.

Error on Install win11 (Python not found)

Models from HuggingFace don't download

I add the HF_TOKEN key to colab and run colab w/ default settings.
It loads the window.
I add the huggingface key to the window.
I keep everything at default settings and hit 'install'
It grabs a handful of files in the notebook and then gets to loading pipline components, which never goes past 0
In the window, it says "Looks like you need to accept the HuggingFace SDXL-Base V1 Model Card to use Checkpoint
Error, no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory /root/.cache/huggingface/hub/models-stabilityai--stable-diffusion-xl-base-1.0/snapshots/bunchofnumbers/text_encoder_2

There is no model card to accept on the huggingface page. I looked it up and apparently they removed this requirement.

[Features Requests]: a few things...perhaps

Hey, really cool UI with a ton of features I'm excited to test out. Just wanted to provide some honest feedback on a few things that seemed a bit odd or confusing to me:

Model downloading:
Not sure where models get downloaded to or how long downloads will take
Would be great to have a download progress bar with estimated time, so I know when models are ready
For example, I started downloading the stable diffusion text2img and img2img models over 10 minutes ago, and it still hasn't completed even though I have a very fast internet connection. A progress bar would help me know if it got stuck or how long I can expect it to take.

Image generating workflow feels fragmented:
Image settings in one tab, prompts in another, generate in a third tab
Would be nicer if it was unified in one generate images tab
Could have subtabs for prompt options, settings, etc

Also unsure if I can generate just one image at a time, or if it has to be batch
Overall it feels less flexible than expected for an app with so many features

Here are some suggestions that I think could help:
Add download progress bar with estimated time on model downloads
Unify image generation in one tab
Tabs or sections for image settings, prompts, options
Allow single image generation, not just batches
Consider more flexibility/customization in the workflow

Let me know if any of that feedback helps! I'm really impressed with the app so far and am looking forward to testing more features once I get past those initial hurdles. Excited to see where this goes!

Unable to start Colab pro once I "Restart session and Run All again."

Hi,

I have Google Colab Pro, and I am trying to run the notebook.

After the first message requesting to "Restart session and Run All again." I go to to the Runtime tab, I select that option, but I am getting this error:

Settings file not found, starting with defaults...
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/content/sdd_colab.py in <module>
  45444 elif tunnel_type == "localtunnel":
  45445     import re
> 45446     localtunnel = subprocess.Popen(['lt', '--port', port, 'http'], stdout=subprocess.PIPE)
  45447     url = str(localtunnel.stdout.readline())
  45448     public_url = (re.search("(?P<url>https?:\/\/[^\s]+loca.lt)", url).group("url"))

1 frames
[/usr/lib/python3.10/subprocess.py](https://localhost:8080/#) in _execute_child(self, args, executable, preexec_fn, close_fds, pass_fds, cwd, env, startupinfo, creationflags, shell, p2cread, p2cwrite, c2pread, c2pwrite, errread, errwrite, restore_signals, gid, gids, uid, umask, start_new_session)
   1794                     fds_to_keep = set(pass_fds)
   1795                     fds_to_keep.add(errpipe_write)
-> 1796                     self.pid = _posixsubprocess.fork_exec(
   1797                             args, executable_list,
   1798                             close_fds, tuple(sorted(map(int, fds_to_keep))),

TypeError: expected str, bytes or os.PathLike object, not int