2022-10-07 22:40:06 +03:00
|
|
|
-e .
|
|
|
|
|
2022-09-20 10:21:47 +03:00
|
|
|
# See: https://github.com/CompVis/taming-transformers/issues/176
|
|
|
|
# -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers # required by ldm
|
|
|
|
# Note: taming package needs to be installed with -e option
|
2022-10-07 22:40:06 +03:00
|
|
|
-e git+https://github.com/CompVis/taming-transformers#egg=taming-transformers
|
|
|
|
invisible-watermark==0.1.5
|
|
|
|
taming-transformers-rom1504==0.0.6 # required by ldm
|
2022-09-20 10:21:47 +03:00
|
|
|
|
2022-10-07 22:40:06 +03:00
|
|
|
# Note: K-diffusion brings in CLIP 1.0 as a dependency automatically; will create a dependency resolution conflict when explicitly specified together
|
|
|
|
git+https://github.com/openai/CLIP.git@main#egg=clip
|
2022-09-20 10:21:47 +03:00
|
|
|
|
|
|
|
git+https://github.com/crowsonkb/k-diffusion.git
|
2022-10-07 22:40:06 +03:00
|
|
|
# git+https://github.com/hlky/k-diffusion-sd#egg=k_diffusion
|
2022-09-25 22:14:10 +03:00
|
|
|
|
|
|
|
# Dependencies required for Stable Diffusion UI
|
|
|
|
pynvml==11.4.1
|
|
|
|
omegaconf==2.2.3
|
|
|
|
|
|
|
|
# Note: Jinja2 3.x major version required due to breaking changes found in markupsafe==2.1.1; 2.0.1 is incompatible with other upstream dependencies
|
|
|
|
# see https://github.com/pallets/markupsafe/issues/304
|
2022-10-07 22:40:06 +03:00
|
|
|
Jinja2==3.1.2 # Jinja2 is required by Gradio
|
2022-09-25 22:14:10 +03:00
|
|
|
|
|
|
|
# Environment Dependencies for WebUI (gradio)
|
2022-10-14 14:54:35 +03:00
|
|
|
gradio==3.4.1
|
2022-09-25 22:14:10 +03:00
|
|
|
|
|
|
|
# Environment Dependencies for WebUI (streamlit)
|
2022-09-27 00:42:02 +03:00
|
|
|
streamlit==1.13.0
|
2022-09-25 22:14:10 +03:00
|
|
|
streamlit-on-Hover-tabs==1.0.1
|
|
|
|
streamlit-option-menu==0.3.2
|
|
|
|
streamlit_nested_layout==0.1.1
|
|
|
|
streamlit-server-state==0.14.2
|
2022-09-30 01:13:21 +03:00
|
|
|
streamlit-tensorboard==0.0.2
|
|
|
|
hydralit==1.0.14
|
|
|
|
hydralit_components==1.0.10
|
2022-10-07 22:40:06 +03:00
|
|
|
stqdm==0.0.4
|
2022-10-20 05:55:34 +03:00
|
|
|
uvicorn
|
|
|
|
fastapi
|
2022-10-23 21:34:27 +03:00
|
|
|
jsonmerge==1.8.
|
|
|
|
matplotlib==3.6.
|
|
|
|
resize-right==0.0.2
|
|
|
|
torchdiffeq==0.2.3
|
2022-10-12 07:52:28 +03:00
|
|
|
|
|
|
|
# txt2vid
|
2022-10-23 12:54:25 +03:00
|
|
|
diffusers==0.6.0
|
2022-10-12 19:41:49 +03:00
|
|
|
librosa==0.9.2
|
2022-09-30 01:13:21 +03:00
|
|
|
|
2022-10-12 07:52:28 +03:00
|
|
|
# img2img inpainting
|
|
|
|
streamlit-drawable-canvas==0.9.2
|
|
|
|
|
2022-09-30 01:13:21 +03:00
|
|
|
# Img2text
|
|
|
|
ftfy==6.1.1
|
|
|
|
fairscale==0.4.4
|
|
|
|
regex
|
Scene-to-Image Prompt Layering System (#1179)
# Summary of the change
- new Scene-to-Image tab
- new scn2img function
- functions for loading and running monocular_depth_estimation with
tensorflow
# Description
(relevant motivation, which issue is fixed)
Related to discussion #925
> Would it be possible to have a layers system where we could do have
foreground, mid, and background objects which relate to one another and
share the style? So we could say generate a landscape, one another layer
generate a castle, and on another layer generate a crowd of people.
To make this work I made a prompt-based layering system in a new
"Scene-to-Image" tab.
You write a a multi-line prompt that looks like markdown, where each
section declares one layer.
It is hierarchical, so each layer can have their own child layers.
Examples: https://imgur.com/a/eUxd5qn
![](https://i.imgur.com/L61w00Q.png)
In the frontend you can find a brief documentation for the syntax,
examples and reference for the various arguments.
Here a short summary:
Sections with "prompt" and child layers are img2img, without child
layers they are txt2img.
Without "prompt" they are just images, useful for mask selection, image
composition, etc.
Images can be initialized with "color", resized with "resize" and their
position specified with "pos".
Rotation and rotation center are "rotation" and "center".
Mask can automatically be selected by color or by estimated depth based
on https://huggingface.co/spaces/atsantiago/Monocular_Depth_Filter.
![](https://i.imgur.com/8rMHWmZ.png)
# Additional dependencies that are required for this change
For mask selection by monocular depth estimation tensorflow is required
and the model must be cloned to ./src/monocular_depth_estimation/
Changes in environment.yaml:
- einops>=0.3.0
- tensorflow>=2.10.0
Einops must be allowed to be newer for tensorflow to work.
# Checklist:
- [x] I have changed the base branch to `dev`
- [x] I have performed a self-review of my own code
- [x] I have commented my code in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
2022-10-02 20:23:37 +03:00
|
|
|
timm==0.6.7
|
2022-09-30 01:13:21 +03:00
|
|
|
tqdm==4.64.0
|
|
|
|
tensorboard==2.10.1
|
2022-09-25 22:14:10 +03:00
|
|
|
|
|
|
|
|
|
|
|
# Other
|
2022-10-07 22:40:06 +03:00
|
|
|
retry==0.9.2 # used by sd_utils
|
|
|
|
python-slugify==6.1.2 # used by sd_utils
|
|
|
|
piexif==1.1.3 # used by sd_utils
|
|
|
|
|
|
|
|
accelerate==0.12.0
|
|
|
|
albumentations==0.4.3
|
|
|
|
einops==0.3.1
|
|
|
|
facexlib>=0.2.3
|
|
|
|
imageio-ffmpeg==0.4.2
|
|
|
|
imageio==2.9.0
|
|
|
|
kornia==0.6
|
|
|
|
loguru
|
|
|
|
opencv-python-headless==4.6.0.66
|
|
|
|
open-clip-torch==2.0.2
|
|
|
|
pandas==1.4.3
|
|
|
|
pudb==2019.2
|
|
|
|
pytorch-lightning==1.7.7
|
|
|
|
realesrgan==0.3.0
|
|
|
|
test-tube>=0.7.5
|
|
|
|
timm==0.6.7
|
|
|
|
torch-fidelity==0.3.0
|
|
|
|
transformers==4.19.2 # do not change
|
|
|
|
wget
|
2022-09-25 22:14:10 +03:00
|
|
|
|
|
|
|
# Optional packages commonly used with Stable Diffusion workflow
|
|
|
|
|
|
|
|
# Upscalers
|
|
|
|
basicsr==1.4.2 # required by RealESRGAN
|
|
|
|
gfpgan==1.3.8 # GFPGAN
|
2022-09-27 06:40:12 +03:00
|
|
|
realesrgan==0.3.0 # RealESRGAN brings in GFPGAN as a requirement
|
2022-10-19 13:27:20 +03:00
|
|
|
-e git+https://github.com/devilismyfriend/latent-diffusion#egg=latent-diffusion
|
2022-09-25 22:14:10 +03:00
|
|
|
|
Scene-to-Image Prompt Layering System (#1179)
# Summary of the change
- new Scene-to-Image tab
- new scn2img function
- functions for loading and running monocular_depth_estimation with
tensorflow
# Description
(relevant motivation, which issue is fixed)
Related to discussion #925
> Would it be possible to have a layers system where we could do have
foreground, mid, and background objects which relate to one another and
share the style? So we could say generate a landscape, one another layer
generate a castle, and on another layer generate a crowd of people.
To make this work I made a prompt-based layering system in a new
"Scene-to-Image" tab.
You write a a multi-line prompt that looks like markdown, where each
section declares one layer.
It is hierarchical, so each layer can have their own child layers.
Examples: https://imgur.com/a/eUxd5qn
![](https://i.imgur.com/L61w00Q.png)
In the frontend you can find a brief documentation for the syntax,
examples and reference for the various arguments.
Here a short summary:
Sections with "prompt" and child layers are img2img, without child
layers they are txt2img.
Without "prompt" they are just images, useful for mask selection, image
composition, etc.
Images can be initialized with "color", resized with "resize" and their
position specified with "pos".
Rotation and rotation center are "rotation" and "center".
Mask can automatically be selected by color or by estimated depth based
on https://huggingface.co/spaces/atsantiago/Monocular_Depth_Filter.
![](https://i.imgur.com/8rMHWmZ.png)
# Additional dependencies that are required for this change
For mask selection by monocular depth estimation tensorflow is required
and the model must be cloned to ./src/monocular_depth_estimation/
Changes in environment.yaml:
- einops>=0.3.0
- tensorflow>=2.10.0
Einops must be allowed to be newer for tensorflow to work.
# Checklist:
- [x] I have changed the base branch to `dev`
- [x] I have performed a self-review of my own code
- [x] I have commented my code in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
2022-10-02 20:23:37 +03:00
|
|
|
## for monocular depth estimation
|
|
|
|
tensorflow==2.10.0
|
|
|
|
|
2022-10-09 13:21:06 +03:00
|
|
|
# Unused Packages: No current usage but will be used in the future.
|
|
|
|
|
|
|
|
|
2022-09-25 22:14:10 +03:00
|
|
|
# Orphaned Packages: No usage found
|
Scene-to-Image Prompt Layering System (#1179)
# Summary of the change
- new Scene-to-Image tab
- new scn2img function
- functions for loading and running monocular_depth_estimation with
tensorflow
# Description
(relevant motivation, which issue is fixed)
Related to discussion #925
> Would it be possible to have a layers system where we could do have
foreground, mid, and background objects which relate to one another and
share the style? So we could say generate a landscape, one another layer
generate a castle, and on another layer generate a crowd of people.
To make this work I made a prompt-based layering system in a new
"Scene-to-Image" tab.
You write a a multi-line prompt that looks like markdown, where each
section declares one layer.
It is hierarchical, so each layer can have their own child layers.
Examples: https://imgur.com/a/eUxd5qn
![](https://i.imgur.com/L61w00Q.png)
In the frontend you can find a brief documentation for the syntax,
examples and reference for the various arguments.
Here a short summary:
Sections with "prompt" and child layers are img2img, without child
layers they are txt2img.
Without "prompt" they are just images, useful for mask selection, image
composition, etc.
Images can be initialized with "color", resized with "resize" and their
position specified with "pos".
Rotation and rotation center are "rotation" and "center".
Mask can automatically be selected by color or by estimated depth based
on https://huggingface.co/spaces/atsantiago/Monocular_Depth_Filter.
![](https://i.imgur.com/8rMHWmZ.png)
# Additional dependencies that are required for this change
For mask selection by monocular depth estimation tensorflow is required
and the model must be cloned to ./src/monocular_depth_estimation/
Changes in environment.yaml:
- einops>=0.3.0
- tensorflow>=2.10.0
Einops must be allowed to be newer for tensorflow to work.
# Checklist:
- [x] I have changed the base branch to `dev`
- [x] I have performed a self-review of my own code
- [x] I have commented my code in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
2022-10-02 20:23:37 +03:00
|
|
|
|
2022-10-09 13:21:06 +03:00
|
|
|
|