Commit Graph

497 Commits

Author SHA1 Message Date
Bryce
f866aaa44d version: 14.0.2 2024-01-03 19:37:44 -08:00
Bryce
e00c7b9eb7 fix: add back missing init file 2024-01-03 19:36:03 -08:00
Bryce
1598469179 version: 14.0.1 2024-01-03 09:02:26 -08:00
Bryce
d148bc1537 fix: progress latent collection bug 2024-01-03 09:01:30 -08:00
Bryce
fdb48399af docs: separate changelog. other small cleanup 2024-01-03 09:01:30 -08:00
Bryce
ed40a12c01 version: 14.0.0 2024-01-02 22:51:41 -08:00
Bryce
57dc27df8c build: tag imaginairy as typed 2024-01-02 22:02:31 -08:00
Bryce
55e27160f5 build: vendorize refiners
so we can still work in conda envs
2024-01-02 22:02:31 -08:00
Bryce
f84406f12c fix: handle unexpected keys in weights better 2024-01-02 20:51:05 -08:00
Bryce
5b3b04b877 build: remove pytorch lightning dependency 2024-01-02 20:51:05 -08:00
Bryce
9f33fa0664 version: 14.0.0b9 2024-01-01 20:17:39 -08:00
Bryce
35a5ccbcba fix: include weightmaps 2024-01-01 20:17:14 -08:00
Bryce
e90bf1b47d version: 14.0.0b8 2024-01-01 20:01:53 -08:00
Bryce
7100d3f9ea perf: make upscaler use fp16 for better efficiency 2024-01-01 19:59:31 -08:00
Bryce
4fcfc363af fix: always show total last 2024-01-01 19:59:31 -08:00
Bryce
f50a1f5b0c fix: interrupted generations don't prevent more generations
fixes #424

- pref: improve memory usage when loading SD15.
- feature: clean up CLI output more
- feature: cuda memory tracking context manager
- feature: use safetensors fp16 for sd15
2024-01-01 19:59:31 -08:00
Bryce
9e3403df89 feature: clean up terminal output
- recording timing and memory usage of various steps
- re-use logging context for composition images
- load sdxl weights in a more VRAM efficient way
- switch to diffusers weights for default weights for sd15
2024-01-01 15:15:31 -08:00
Bryce
0d78b8271f version: 14.0.0b7 2024-01-01 15:15:31 -08:00
Bryce Drennan
77c4b85037
perf: improve memory usage (#433)
add warning for corrupt weights files
2023-12-29 09:04:33 -08:00
Bryce
26d1ff9bc4 version: 14.0.0b6 2023-12-27 22:23:21 -08:00
Bryce Drennan
42a045e8e6
feature: support sdxl (#431)
- adds support for (SDXL)[https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0]
  - adds sliced encoding/decoding to refiners sdxl pipeline
  - doesn't support inpainting, controlnets
- monkeypatches self_attention_guidance to use sliced attention
- adds a bunch of model weight translation utilities and weightmaps
- add [opendalle 1.1](https://huggingface.co/dataautogpt3/OpenDalleV1.1)
- change default model to opendalle
- fix: better handle special characters in path inputs on command line
**todo**
- add tests
2023-12-27 21:52:37 -08:00
jaydrennan
fb7cff3684
Merge pull request #430 from brycedrennan/ruff_formatter
Ruff formatter
2023-12-27 18:51:15 -07:00
jaydrennan
3322777f5e refactor: formatting changes ruff formatter
ruff formatter has slight differences in formatting compared to black
2023-12-27 17:08:01 -08:00
jaydrennan
7eef3bf628 feature: replaces black formatter with ruff formatter 2023-12-27 17:08:01 -08:00
Bryce Drennan
a2c38b3ec0
feature: support loading diffusers folder/based models from huggingface (#427) 2023-12-21 14:24:35 -08:00
Bryce
50e796a3b7 refactor: move code around 2023-12-21 05:48:02 -08:00
Bryce
32b5175e0e feature: better upscaling
- use face enhancement in a smarter way that doesn't blur high-res images
- use a different upscale model for composition images

**Upscaling**
RealESRGAN is great but it blurs parts of images it doesn't understand

4xUltrasharp is a finetune of RealESRGan that isn't as good but doesn't have this blurry patch problem.  This makes it more suitable to use as part of the composition/upscale process.  We still use realesrgan for any last-step upscales since it does look better.

had to write a state dict translator to use the ultrasharp model

**Face Enhancement**

We no longer enhance faces that are larger than 512 pixels. They should already have enough details and the face enhancer doesn't produce faces at high enough resolution to look good at that size.
2023-12-21 05:48:02 -08:00
Bryce
6ebd12abb1 refactor: move code to more intuitive places 2023-12-21 05:48:02 -08:00
Bryce
8cfb46d6de fix: bug in sliced encoder 2023-12-21 05:48:02 -08:00
Bryce
372453e645 refactor: remove training code 2023-12-21 05:48:02 -08:00
Bryce Drennan
616f686ed2
small changes (#425)
* docs: update todo

* refactor: small cleanup of tiling code
2023-12-19 12:39:34 -08:00
Bryce
d834e8b5b3 test: run non-gpu tests on github 2023-12-18 21:24:59 -08:00
jaydrennan
df00109074 refactor: space formatting 2023-12-18 21:24:59 -08:00
jaydrennan
d39486af54 fix: updates test marking to use nodeid instead of name 2023-12-18 21:24:59 -08:00
jaydrennan
0c01cd690f
fix: sets correct default value for composition strength. (#422)
also corrects positional argument error by requiring _imagine_cmd to take key word arguments.
2023-12-18 17:31:57 -08:00
Bryce
0c03612d44 feature: large images now stay well-composed thanks to tile controlnet 2023-12-18 15:33:25 -08:00
jaydrennan
2372a71e6c fix: adds tile/detail controlnet back in. 2023-12-18 15:33:25 -08:00
Bryce Drennan
f88b5c1b2b
fix: word images still work without specified size (#421) 2023-12-18 15:09:23 -08:00
Bryce
7880ee1389 feature: update midas (depth maps) 2023-12-18 13:01:56 -08:00
Bryce
bf14ee6ee6 feature: add christmas-scene phrase list
Also add script that uses chatgpt to generate phrase-lists
2023-12-18 13:01:56 -08:00
Bryce
c6ac5f553a refactor: separate controlnet image preprocessing 2023-12-18 13:01:56 -08:00
Bryce
9a0e0cd1a7 feature: better depth maps 2023-12-18 13:01:56 -08:00
jaydrennan
2eee741b20
Merge pull request #418 from brycedrennan/fix_test_set_spu_full
fix: configures test_set_gpu_full to run on a m1 mac.
2023-12-17 23:50:46 -07:00
jaydrennan
c99a169986 fix: configures test_set_gpu_full to run on a m1 mac. 2023-12-17 22:35:12 -08:00
Bryce Drennan
2144f26fa7
feature: add ability to dynamically make word images (#417) 2023-12-16 22:08:19 -08:00
jaydrennan
3bd3dfdeaf
feature: adds --composition-strength parameter to cli (#416) 2023-12-16 14:40:06 -08:00
jaydrennan
41a9d7007b
test: adds tests for stablestudio (#415) 2023-12-16 12:00:03 -08:00
jaydrennan
e1e6f8037c
refactor: removes unused code and configurations (#405)
Co-authored-by: jaydrennan
2023-12-15 15:27:00 -08:00
Bryce
6d39d791b1 refactor: move safety to utils 2023-12-15 14:32:01 -08:00
Bryce
168a843f29 refactor: move colorize to api 2023-12-15 14:32:01 -08:00