Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update README.md for 14.0.0 #394

Merged
merged 3 commits into from
Nov 23, 2023
Merged

Update README.md for 14.0.0 #394

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1491665
refactor: updates README for 14.0.0
Nov 22, 2023
90e32bc
refactor: removes outdated info and spelling error
Nov 22, 2023
fd02b3f
refactor: removes unused model configs
Nov 22, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 14 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ Visit http://localhost:8000/ and http://localhost:8000/docs
<img src="https://github.com/Stability-AI/StableStudio/blob/a65d4877ad7d309627808a169818f1add8c278ae/misc/GenerateScreenshot.png?raw=true">

### Image Structure Control [by ControlNet](https://github.com/lllyasviel/ControlNet)
#### (Broken as of 14.0.0)
Generate images guided by body poses, depth maps, canny edges, hed boundaries, or normal maps.

**Openpose Control**
Expand Down Expand Up @@ -156,6 +157,7 @@ aimg colorize pearl-girl.jpg --caption "photo of a woman"
</p>

### Instruction based image edits [by InstructPix2Pix](https://github.com/timothybrooks/instruct-pix2pix)
#### (Broken as of 14.0.0)
Just tell imaginairy how to edit the image and it will do it for you!
<p float="left">
<img src="assets/scenic_landscape_winter.jpg" height="256">
Expand Down Expand Up @@ -325,10 +327,7 @@ Example:
### Work with different generation models

<p float="left">
<img src="assets/fairytale-treehouse-sd14.jpg" height="256">
<img src="assets/fairytale-treehouse-sd15.jpg" height="256">
<img src="assets/fairytale-treehouse-sd20.jpg" height="256">
<img src="assets/fairytale-treehouse-sd21.jpg" height="256">
<img src="assets/fairytale-treehouse-openjourney-v1.jpg" height="256">
<img src="assets/fairytale-treehouse-openjourney-v2.jpg" height="256">
</p>
Expand Down Expand Up @@ -493,6 +492,17 @@ A: The AI models are cached in `~/.cache/` (or `HUGGINGFACE_HUB_CACHE`). To dele

## ChangeLog

**14.0.0**
- 🎉 feature: uses refiners library for generation
- 🎉 feature: adds support for pytorch 2.0
- fix: stable diffusion 1.5 + inpainting working
- fix: self-attention guidance working. improves image generation quality
- fix: tile-mode working
- fix: self-attention guidance working. improves image generation quality
- deprecated: support for python 3.8
- deprecated: support for sd 1.4, 2.0, 2.1
- broken: pix2pix editing, most samplers, most controlnets, and memory management

**13.2.1**
- fix: pydantic models for http server working now. Fixes #380
- fix: install triton so annoying message is gone
Expand Down Expand Up @@ -714,7 +724,7 @@ Use with `--model SD-2.1` or `--model SD-2.0-v`
- fix: version metadata was broken

**6.1.0**
- feature: use different default steps and image sizes depending on sampler and model selceted
- feature: use different default steps and image sizes depending on sampler and model selected
- fix: #110 use proper version in image metadata
- refactor: samplers all have their own class that inherits from ImageSampler
- feature: 🎉🎉🎉 Stable Diffusion 2.0
Expand Down Expand Up @@ -836,7 +846,6 @@ would be uncorrelated to the rest of the surrounding image. It created terrible


## Not Supported
- a GUI. this is a python library
- exploratory features that don't work well


65 changes: 0 additions & 65 deletions imaginairy/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,14 +31,6 @@ class ModelConfig:
midas_url = "https://github.com/intel-isl/DPT/releases/download/1_0/dpt_hybrid-midas-501f0c75.pt"

MODEL_CONFIGS = [
# ModelConfig(
# description="Stable Diffusion 1.4",
# short_name="SD-1.4",
# config_path="configs/stable-diffusion-v1.yaml",
# weights_url="https://huggingface.co/bstddev/sd-v1-4/resolve/77221977fa8de8ab8f36fac0374c120bd5b53287/sd-v1-4.ckpt",
# default_image_size=512,
# alias="sd14",
# ),
ModelConfig(
description="Stable Diffusion 1.5",
short_name="SD-1.5",
Expand All @@ -57,63 +49,6 @@ class ModelConfig:
alias="sd15in",
),
# ModelConfig(
# description="Stable Diffusion 2.0 - bad at making people",
# short_name="SD-2.0",
# config_path="configs/stable-diffusion-v2-inference.yaml",
# weights_url="https://huggingface.co/stabilityai/stable-diffusion-2-base/resolve/main/512-base-ema.ckpt",
# default_image_size=512,
# alias="sd20",
# ),
# ModelConfig(
# description="Stable Diffusion 2.0 - Inpainting",
# short_name="SD-2.0-inpaint",
# config_path="configs/stable-diffusion-v2-inpainting-inference.yaml",
# weights_url="https://huggingface.co/stabilityai/stable-diffusion-2-inpainting/resolve/main/512-inpainting-ema.ckpt",
# default_image_size=512,
# alias="sd20in",
# ),
# ModelConfig(
# description="Stable Diffusion 2.0 v - 768x768 - bad at making people",
# short_name="SD-2.0-v",
# config_path="configs/stable-diffusion-v2-inference-v.yaml",
# weights_url="https://huggingface.co/stabilityai/stable-diffusion-2/resolve/main/768-v-ema.ckpt",
# default_image_size=768,
# alias="sd20v",
# ),
# ModelConfig(
# description="Stable Diffusion 2.0 - Depth",
# short_name="SD-2.0-depth",
# config_path="configs/stable-diffusion-v2-midas-inference.yaml",
# weights_url="https://huggingface.co/stabilityai/stable-diffusion-2-depth/resolve/main/512-depth-ema.ckpt",
# default_image_size=512,
# alias="sd20dep",
# ),
# ModelConfig(
# description="Stable Diffusion 2.1",
# short_name="SD-2.1",
# config_path="configs/stable-diffusion-v2-inference.yaml",
# weights_url="https://huggingface.co/stabilityai/stable-diffusion-2-1-base/resolve/main/v2-1_512-ema-pruned.ckpt",
# default_image_size=512,
# alias="sd21",
# ),
# ModelConfig(
# description="Stable Diffusion 2.1 - Inpainting",
# short_name="SD-2.1-inpaint",
# config_path="configs/stable-diffusion-v2-inpainting-inference.yaml",
# weights_url="https://huggingface.co/stabilityai/stable-diffusion-2-inpainting/resolve/main/512-inpainting-ema.ckpt",
# default_image_size=512,
# alias="sd21in",
# ),
# ModelConfig(
# description="Stable Diffusion 2.1 v - 768x768",
# short_name="SD-2.1-v",
# config_path="configs/stable-diffusion-v2-inference-v.yaml",
# weights_url="https://huggingface.co/stabilityai/stable-diffusion-2-1/resolve/main/v2-1_768-ema-pruned.ckpt",
# default_image_size=768,
# forced_attn_precision="fp32",
# alias="sd21v",
# ),
# ModelConfig(
# description="Instruct Pix2Pix - Photo Editing",
# short_name="instruct-pix2pix",
# config_path="configs/instruct-pix2pix.yaml",
Expand Down
Loading