Archives/imaginAIry
2
0
Fork 0
mirror of https://github.com/brycedrennan/imaginAIry synced 2024-11-05 12:00:15 +00:00
Code Issues Packages Projects Releases Wiki Activity
146 Commits 10 Branches 104 Tags 322 MiB
Python 99.4%
Makefile 0.6%
4ba1965db8
Go to file
Bryce 4ba1965db8 feature: k-diff sampler img2img and masking
2022-10-14 03:23:16 -07:00
.github ci: faster linting? 2022-10-11 01:06:24 -05:00
assets feature: prompt expansion (#51) 2022-10-08 18:34:35 -07:00
docs Update emad-qa-2020-10-10.md 2022-10-12 10:40:02 -07:00
imaginairy feature: k-diff sampler img2img and masking 2022-10-14 03:23:16 -07:00
scripts feature: prompt expansion (#51) 2022-10-08 18:34:35 -07:00
tests feature: k-diff sampler img2img and masking 2022-10-14 03:23:16 -07:00
.dockerignore tests: add docker image for testing environment. minor test improvements 2022-09-21 22:38:44 -07:00
.gitignore fix: inpainting producing blurry images 2022-09-27 17:19:25 -07:00
Dockerfile feature: urls as init images 2022-09-15 23:06:59 -07:00
LICENSE docs: update readme. add docs to package 2022-09-11 21:36:14 -07:00
Makefile feature: prompt expansion (#51) 2022-10-08 18:34:35 -07:00
README.md feature: k-diff sampler img2img and masking 2022-10-14 03:23:16 -07:00
requirements-dev.in tests: tests can run without any network calls 2022-10-11 01:06:24 -05:00
requirements-dev.txt tests: tests can run without any network calls 2022-10-11 01:06:24 -05:00
setup.py fix: k-sampler methods were broken 2022-10-12 20:35:45 -07:00
STABLE_DIFFUSION_LICENSE refactor: simplify structure 2022-09-11 00:59:03 -07:00
tox.ini tests: add some utils tests 2022-10-07 00:02:26 -05:00

README.md

ImaginAIry 🤖🧠

AI imagined images. Pythonic generation of stable diffusion images.

"just works" on Linux and macOS(M1) (and maybe windows?).

Examples

# on macOS, make sure rust is installed first
>> pip install imaginairy
>> imagine "a scenic landscape" "a photo of a dog" "photo of a fruit bowl" "portrait photo of a freckled woman"
Console Output 
🤖🧠 received 4 prompt(s) and will repeat them 1 times to create 4 images.
Loading model onto mps backend...
Generating 🖼  : "a scenic landscape" 512x512px seed:557988237 prompt-strength:7.5 steps:40 sampler-type:PLMS
    PLMS Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 40/40 [00:29<00:00,  1.36it/s]
    🖼  saved to: ./outputs/000001_557988237_PLMS40_PS7.5_a_scenic_landscape.jpg
Generating 🖼  : "a photo of a dog" 512x512px seed:277230171 prompt-strength:7.5 steps:40 sampler-type:PLMS
    PLMS Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 40/40 [00:28<00:00,  1.41it/s]
    🖼  saved to: ./outputs/000002_277230171_PLMS40_PS7.5_a_photo_of_a_dog.jpg
Generating 🖼  : "photo of a fruit bowl" 512x512px seed:639753980 prompt-strength:7.5 steps:40 sampler-type:PLMS
    PLMS Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 40/40 [00:28<00:00,  1.40it/s]
    🖼  saved to: ./outputs/000003_639753980_PLMS40_PS7.5_photo_of_a_fruit_bowl.jpg
Generating 🖼  : "portrait photo of a freckled woman" 512x512px seed:500686645 prompt-strength:7.5 steps:40 sampler-type:PLMS
    PLMS Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 40/40 [00:29<00:00,  1.37it/s]
    🖼  saved to: ./outputs/000004_500686645_PLMS40_PS7.5_portrait_photo_of_a_freckled_woman.jpg


Prompt Based Editing by clipseg

Specify advanced text based masks using boolean logic and strength modifiers. Mask descriptions must be lowercase. Keywords uppercase. Valid symbols: AND, OR, NOT, (), and mask strength modifier {*1.5} where + can be any of + - * /. Single-character boolean operators also work. When writing strength modifies know that pixel values are between 0 and 1.

>> imagine \
    --init-image pearl_earring.jpg \ 
    --mask-prompt "face AND NOT (bandana OR hair OR blue fabric){*6}" \
    --mask-mode keep \
    --init-image-strength .2 \
    --fix-faces \
    "a modern female president" "a female robot" "a female doctor" "a female firefighter"

➡️ 

>> imagine \
    --init-image fruit-bowl.jpg \
    --mask-prompt "fruit OR fruit stem{*6}" \
    --mask-mode replace \
    --mask-modify-original \
    --init-image-strength .1 \
    "a bowl of kittens" "a bowl of gold coins" "a bowl of popcorn" "a bowl of spaghetti"

➡️

Face Enhancement by CodeFormer

>> imagine "a couple smiling" --steps 40 --seed 1 --fix-faces

➡️

Upscaling by RealESRGAN

>> imagine "colorful smoke" --steps 40 --upscale

➡️

Tiled Images

>> imagine  "gold coins" "a lush forest" "piles of old books" leaves --tile


Image-to-Image

>> imagine "portrait of a smiling lady. oil painting" --init-image girl_with_a_pearl_earring.jpg

➡️

Prompt Expansion

You can use {} to randomly pull values from lists. A list of values separated by | and enclosed in { } will be randomly drawn from in a non-repeating fashion. Values that are surrounded by _ _ will pull from a phrase list of the same name. Folders containing .txt phraselist files may be specified via --prompt_library_path. The option may be specified multiple times. Built-in categories:

  3d-term, adj-architecture, adj-beauty, adj-detailed, adj-emotion, adj-general, adj-horror, animal, art-movement, 
  art-site, artist, artist-botanical, artist-surreal, aspect-ratio, bird, body-of-water, body-pose, camera-brand,
  camera-model, color, cosmic-galaxy, cosmic-nebula, cosmic-star, cosmic-term, dinosaur, eyecolor, f-stop, 
  fantasy-creature, fantasy-setting, fish, flower, focal-length, food, fruit, games, gen-modifier, hair, hd,
  iso-stop, landscape-type, national-park, nationality, neg-weight, noun-beauty, noun-fantasy, noun-general, 
  noun-horror, occupation, photo-term, pop-culture, pop-location, punk-style, quantity, rpg-item, scenario-desc, 
  skin-color, spaceship, style, tree-species, trippy, world-heritage-site

Examples:

imagine "a {lime|blue|silver|aqua} colored dog" -r 4 --seed 0 (note that it generates a dog of each color without repetition)

imagine "a {_color_} dog" -r 4 --seed 0 will generate four, different colored dogs. The colors will be pulled from an included phraselist of colors.

imagine "a {_spaceship_|_fruit_|hot air balloon}. low-poly" -r 4 --seed 0 will generate images of spaceships or fruits or a hot air balloon

Credit to noodle-soup-prompts where most, but not all, of the wordlists originate.

Generate image captions (via BLIP)

>> aimg describe assets/mask_examples/bowl001.jpg
a bowl full of gold bars sitting on a table

Features

  • It makes images from text descriptions! 🎉
  • Generate images either in code or from command line.
  • It just works. Proper requirements are installed. model weights are automatically downloaded. No huggingface account needed. (if you have the right hardware... and aren't on windows)
  • No more distorted faces!
  • Noisy logs are gone (which was surprisingly hard to accomplish)
  • WeightedPrompts let you smash together separate prompts (cat-dog)
  • Tile Mode creates tileable images
  • Prompt metadata saved into image file metadata
  • Edit images by describing the part you want edited (see example above)
  • Have AI generate captions for images aimg describe <filename-or-url>
  • Interactive prompt: just run aimg

How To

For full command line instructions run aimg --help

from imaginairy import imagine, imagine_image_files, ImaginePrompt, WeightedPrompt, LazyLoadingImage

url = "https://upload.wikimedia.org/wikipedia/commons/thumb/6/6c/Thomas_Cole_-_Architect%E2%80%99s_Dream_-_Google_Art_Project.jpg/540px-Thomas_Cole_-_Architect%E2%80%99s_Dream_-_Google_Art_Project.jpg"
prompts = [
    ImaginePrompt("a scenic landscape", seed=1, upscale=True),
    ImaginePrompt("a bowl of fruit"),
    ImaginePrompt([
        WeightedPrompt("cat", weight=1),
        WeightedPrompt("dog", weight=1),
    ]),
    ImaginePrompt(
        "a spacious building", 
        init_image=LazyLoadingImage(url=url)
    ),
    ImaginePrompt(
        "a bowl of strawberries", 
        init_image=LazyLoadingImage(filepath="mypath/to/bowl_of_fruit.jpg"),
        mask_prompt="fruit OR stem{*2}",  # amplify the stem mask x2
        mask_mode="replace",
        mask_modify_original=True,
    ),
    ImaginePrompt("strawberries", tile_mode=True),
]
for result in imagine(prompts):
    # do something
    result.save("my_image.jpg")

# or

imagine_image_files(prompts, outdir="./my-art")

Requirements

  • ~10 gb space for models to download
  • A decent computer with either a CUDA supported graphics card or M1 processor.
  • Python installed. Preferably Python 3.10.
  • For macOS rust and setuptools-rust must be installed to compile the tokenizer library. They can be installed via: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh and pip install setuptools-rust

Running in Docker

See example Dockerfile (works on machine where you can pass the gpu into the container)

docker build . -t imaginairy
# you really want to map the cache or you end up wasting a lot of time and space redownloading the model weights
docker run -it --gpus all -v $HOME/.cache/huggingface:/root/.cache/huggingface -v $HOME/.cache/torch:/root/.cache/torch -v `pwd`/outputs:/outputs imaginairy /bin/bash

Running on Google Colab

Example Colab

ChangeLog

3.1.0

  • feature: img2img/inpainting supported on all samplers
  • refactor: consolidates img2img/txt2img code. consolidates schedules. consolidates masking
  • ci: minor logging improvements

3.0.1

  • fix: k-samplers were broken

3.0.0

  • feature: improved safety filter

2.4.0

  • 🎉 feature: prompt expansion
  • feature: make (blip) photo captions more descriptive

2.3.1

  • fix: face fidelity default was broken

2.3.0

  • feature: model weights file can be specified via --model-weights-path argument at the command line
  • fix: set face fidelity default back to old value
  • fix: handle small images without throwing exception. credit to @NiclasEriksen
  • docs: add setuptools-rust as dependency for macos

2.2.1

  • fix: init image is fully ignored if init-image-strength = 0

2.2.0

  • feature: face enhancement fidelity is now configurable

2.1.0

2.0.3

  • fix memory leak in face enhancer
  • fix blurry inpainting
  • fix for pillow compatibility

2.0.0

  • 🎉 fix: inpainted areas correlate with surrounding image, even at 100% generation strength. Previously if the generation strength was high enough the generated image would be uncorrelated to the rest of the surrounding image. It created terrible looking images.
  • 🎉 feature: interactive prompt added. access by running aimg
  • 🎉 feature: Specify advanced text based masks using boolean logic and strength modifiers. Mask descriptions must be lowercase. Keywords uppercase. Valid symbols: AND, OR, NOT, (), and mask strength modifier {+0.1} where + can be any of + - * /. Single character boolean operators also work (|, &, !)
  • 🎉 feature: apply mask edits to original files with mask_modify_original (on by default)
  • feature: auto-rotate images if exif data specifies to do so
  • fix: mask boundaries are more accurate
  • fix: accept mask images in command line
  • fix: img2img algorithm was wrong and wouldn't at values close to 0 or 1

1.6.2

  • fix: another bfloat16 fix

1.6.1

  • fix: make sure image tensors come to the CPU as float32 so there aren't compatability issues with non-bfloat16 cpus

1.6.0

  • fix: maybe address #13 with expected scalar type BFloat16 but found Float
    • at minimum one can specify --precision full now and that will probably fix the issue
  • feature: tile mode can now be specified per-prompt

1.5.3

  • fix: missing config file for describe feature

1.5.1

  • img2img now supported with PLMS (instead of just DDIM)
  • added image captioning feature aimg describe dog.jpg => a brown dog sitting on grass
  • added new commandline tool aimg for additional image manipulation functionality

1.4.0

  • support multiple additive targets for masking with | symbol. Example: "fruit|stem|fruit stem"

1.3.0

  • added prompt based image editing. Example: "fruit => gold coins"
  • test coverage improved

1.2.0

  • allow urls as init-images

previous

  • img2img actually does # of steps you specify
  • performance optimizations
  • numerous other changes

Not Supported

  • a GUI. this is a python library
  • training
  • exploratory features that don't work well

Todo

Noteable Stable Diffusion Implementations

Online Stable Diffusion Services

Further Reading