filipstrand
|
e32be7bf31
|
Update reference test images to match output (mlx=v0.22.0 and changed precision in attention mask)
Noticeable differences in images, but should be OK
|
2025-01-14 22:15:01 +01:00 |
|
filipstrand
|
16a0225b41
|
Specify precision for causal attention mask
|
2025-01-14 21:32:02 +01:00 |
|
Filip Strand
|
3b0f5a4516
|
Merge pull request #116 from filipstrand/optimizations
Optimizations and small refactoring of attention blocks
|
2025-01-14 21:18:04 +01:00 |
|
filipstrand
|
9954e7fb45
|
Unify attention mechanism in single and joint attention blocks
|
2025-01-14 20:16:48 +01:00 |
|
filipstrand
|
f0e82ad67f
|
Optimization: Use fast SDPA (no speedup for me on tests, but a bit cleaner)
Had to update reference test images, but visually no difference
|
2025-01-14 20:16:23 +01:00 |
|
filipstrand
|
0eb8f5082e
|
Update README with perf. update, installation issue and version link
|
2024-12-26 21:03:54 +01:00 |
|
filipstrand
|
2ebb0d1c6e
|
Bump version to v.0.5.1
|
2024-12-23 12:40:19 +01:00 |
|
filipstrand
|
4c0aff9168
|
Fix bug with quantization level being str instead of int
|
2024-12-23 12:21:06 +01:00 |
|
Filip Strand
|
f725583bb9
|
Merge pull request #83 from filipstrand/dreambooth
DreamBooth support
|
2024-12-22 20:02:11 +01:00 |
|
filipstrand
|
bae49c8145
|
Dreambooth v1
|
2024-12-22 19:42:37 +01:00 |
|
filipstrand
|
627398f531
|
Add 'FLUX.1 Tools' for features to support
|
2024-11-21 21:31:27 +01:00 |
|
filipstrand
|
d69f49f31f
|
Add In-Context LoRA for the cool research section
|
2024-11-20 00:18:29 +01:00 |
|
filipstrand
|
121a4f1695
|
Update reference test images to be compatible with mlx>0.19.0 (still visually identical)
|
2024-11-16 20:09:29 +01:00 |
|
filipstrand
|
6350c6fb12
|
Add command to find system spec
|
2024-11-16 16:50:17 +01:00 |
|
filipstrand
|
07c34a9f97
|
Add device mac device to performance table
|
2024-11-16 16:50:17 +01:00 |
|
filipstrand
|
8d7a2eb4fd
|
Add M4 Pro performance numbers
|
2024-11-16 16:50:17 +01:00 |
|
filipstrand
|
2e297a068e
|
Sort performance benchmarks based on performance
|
2024-11-16 16:50:17 +01:00 |
|
Filip Strand
|
c94ab4749d
|
Merge pull request #96 from ivanfioravanti/patch-1
Update README.md
|
2024-11-16 16:00:48 +01:00 |
|
Ivan Fioravanti
|
457b3e9867
|
Update README.md
M4 Max results added
|
2024-11-15 18:42:30 +01:00 |
|
filipstrand
|
e0c9086d0f
|
Update related projects section in README
|
2024-11-10 19:54:45 +01:00 |
|
filipstrand
|
f6bec3cc91
|
fix name
|
2024-11-09 22:13:59 +01:00 |
|
filipstrand
|
e5ae68f312
|
Add new sections in README for "related projects" and "features/research to support"
|
2024-11-09 21:48:15 +01:00 |
|
Filip Strand
|
f78144001c
|
Merge pull request #90 from anthonywu/py13-dev-working
Issue #74 - python 3.13 pip install now working
|
2024-11-09 19:58:55 +01:00 |
|
Anthony Wu
|
08b390dc7b
|
more details for usage
|
2024-11-09 08:19:02 -08:00 |
|
Anthony Wu
|
48d2e71207
|
add dev note that community whl is available now
|
2024-11-08 00:51:53 -08:00 |
|
Anthony Wu
|
391d29fe4f
|
solve python 3.13 pip install
|
2024-11-07 00:01:54 -08:00 |
|
filipstrand
|
4788bbe184
|
Bump version to 0.4.1
|
2024-10-29 20:36:37 +01:00 |
|
Filip Strand
|
909c451001
|
Merge pull request #87 from filipstrand/fix-img2img-for-non-square-resolution
Fix img2img for non-square resolutions
|
2024-10-29 20:24:10 +01:00 |
|
filipstrand
|
ce387921c5
|
Add named args for height and width for clarity
|
2024-10-29 20:12:50 +01:00 |
|
filipstrand
|
82973f9e95
|
Fix bug: swap width <--> height
|
2024-10-29 20:12:50 +01:00 |
|
filipstrand
|
8d93f3e24f
|
Change img2img test to be non-square
|
2024-10-29 20:12:50 +01:00 |
|
filipstrand
|
4e2a10b1b9
|
Rewrite img2img latent creation to emphasize the linear interp between latent and noise
|
2024-10-29 19:19:59 +01:00 |
|
filipstrand
|
8ac08f7853
|
Update readme with new performance numbers
|
2024-10-28 19:27:18 +01:00 |
|
filipstrand
|
506f56ad49
|
Add missing separator
|
2024-10-28 00:34:28 +01:00 |
|
filipstrand
|
ea6202b49f
|
Add img2img example in readme
|
2024-10-28 00:32:57 +01:00 |
|
filipstrand
|
4b173dc818
|
Update readme with img2img example
|
2024-10-28 00:26:06 +01:00 |
|
Filip Strand
|
7f0db775e9
|
Merge pull request #81 from anthonywu/regen-from-metadata
support metadata files as CLI arg supplier
|
2024-10-27 21:15:38 +01:00 |
|
Anthony Wu
|
960447f92e
|
update type hint
|
2024-10-26 20:24:28 -07:00 |
|
Anthony Wu
|
98d7ef5751
|
update: do not require model arg, add controlnet_save_canny, fix bugs, add tests
|
2024-10-26 20:22:32 -07:00 |
|
Anthony Wu
|
ffaf562a8c
|
fix type hint in test file
|
2024-10-26 10:29:33 -07:00 |
|
Anthony Wu
|
351cc8bbf1
|
support metadata files as CLI arg supplier
|
2024-10-20 09:18:49 -07:00 |
|
filipstrand
|
2ed0628e58
|
Light refactoring: Move latent creation to separate class
|
2024-10-20 11:49:43 +02:00 |
|
filipstrand
|
f08c667e1a
|
Remove vae type alias from runtime_config.py
|
2024-10-20 11:05:45 +02:00 |
|
Filip Strand
|
429b580b04
|
Merge pull request #82 from anthonywu/fixes-for-image-to-image
tests and fixes for image to image
|
2024-10-20 11:01:42 +02:00 |
|
Anthony Wu
|
1160d4e8b2
|
controlnet files: revert the refactoring done in #77
|
2024-10-20 01:06:02 -07:00 |
|
Anthony Wu
|
6201a93d4a
|
tests and fixes for image to image
|
2024-10-20 00:48:45 -07:00 |
|
Filip Strand
|
231b9885b8
|
Merge pull request #77 from anthonywu/image-to-image
`mflux-generate` – support image-to-image
|
2024-10-19 15:00:07 +02:00 |
|
Anthony Wu
|
f963b7a9b2
|
image to image implementation
|
2024-10-12 10:46:20 -07:00 |
|
Filip Strand
|
7a0c5f8fe5
|
Merge pull request #75 from anthonywu/argparser-refactor
argparser refactor
|
2024-10-12 14:41:17 +02:00 |
|
filipstrand
|
9c7e857082
|
Add type hinting to CommandLineParser
|
2024-10-12 14:35:11 +02:00 |
|