filipstrand
|
d10e6f4019
|
Add support for converting between LoRA formats
|
2024-09-13 20:37:56 +02:00 |
|
filipstrand
|
7d27f1c4c1
|
Adjust FF block only if it exists
|
2024-09-12 21:18:01 +02:00 |
|
filipstrand
|
3739a6b914
|
Link to madroid 4-bit
|
2024-09-10 19:00:20 +02:00 |
|
filipstrand
|
fe0d01495f
|
Suggest first setting up a venv when installing
|
2024-09-09 18:52:43 +02:00 |
|
filipstrand
|
9d4027698c
|
Default to latest mflux package
|
2024-09-07 12:31:53 +02:00 |
|
Filip Strand
|
0a90939bcc
|
Merge pull request #32 from filipstrand/PyPI-release
PyPI Release
|
2024-09-07 10:53:43 +02:00 |
|
filipstrand
|
a2965a1833
|
Skip python-requires for now
|
2024-09-06 22:59:03 +02:00 |
|
filipstrand
|
2510965027
|
Swap setup.py for pyproject.toml
|
2024-09-06 22:59:03 +02:00 |
|
filipstrand
|
1769baa382
|
Define custom commands for image generation and model saving
|
2024-09-06 22:33:48 +02:00 |
|
filipstrand
|
1567a01745
|
Rename run to generate
|
2024-09-06 22:27:24 +02:00 |
|
filipstrand
|
2a7ca560a2
|
Update installation guide
|
2024-09-06 22:15:06 +02:00 |
|
filipstrand
|
c0d419777e
|
Add quantize option to from_alias initializer
|
2024-09-06 22:11:00 +02:00 |
|
filipstrand
|
af73966f11
|
Fix system paths
|
2024-09-06 21:45:02 +02:00 |
|
filipstrand
|
b9ff93ea3f
|
Fix imports
|
2024-09-06 21:15:46 +02:00 |
|
filipstrand
|
ea3362e8ab
|
Revert "Temporarily allow .jpg and .png before renaming"
This reverts commit 893f6be9bb.
|
2024-09-06 21:10:34 +02:00 |
|
filipstrand
|
00a556cbf2
|
Add setup.py
|
2024-09-06 21:10:33 +02:00 |
|
filipstrand
|
23e44c768b
|
Rename main.py to run.py
|
2024-09-06 21:09:50 +02:00 |
|
filipstrand
|
b8102f2a2f
|
Move main.py and save.py one level down
|
2024-09-06 21:09:44 +02:00 |
|
filipstrand
|
915f3c2950
|
Move flux.py to separate package
|
2024-09-06 21:09:26 +02:00 |
|
filipstrand
|
d2b38011ad
|
Rename flux_1 to mflux
|
2024-09-06 21:09:16 +02:00 |
|
filipstrand
|
893f6be9bb
|
Temporarily allow .jpg and .png before renaming
|
2024-09-06 21:09:02 +02:00 |
|
Filip Strand
|
5b0bd4b7e7
|
Merge pull request #27 from filipstrand/save-image-info
Save image info
|
2024-09-06 20:23:28 +02:00 |
|
filipstrand
|
8e4e8f68d6
|
Fix example
|
2024-09-06 20:20:11 +02:00 |
|
filipstrand
|
6fb51170de
|
Also save LoRA metadata
|
2024-09-06 20:09:27 +02:00 |
|
filipstrand
|
6d05f5b27e
|
Fix saving bug
|
2024-09-06 20:09:17 +02:00 |
|
filipstrand
|
1db28b7ffe
|
Fix example
|
2024-09-06 20:09:06 +02:00 |
|
filipstrand
|
fab10cc046
|
Add proper image class and save metadata
|
2024-09-06 19:38:34 +02:00 |
|
Filip Strand
|
97dc64436e
|
Merge pull request #31 from Xuzzo/fix/width_height_mixup
Fix width and height in config
|
2024-09-06 10:02:46 +02:00 |
|
Filip Strand
|
5431c9faa5
|
Merge pull request #30 from elitexp/main
Apply lora with --apply-lora <path-to-safetensors>
|
2024-09-05 23:28:33 +02:00 |
|
filipstrand
|
50c567c187
|
Fix link
|
2024-09-05 23:26:11 +02:00 |
|
filipstrand
|
1d8714d3b1
|
Add some example runs
|
2024-09-05 23:21:48 +02:00 |
|
filipstrand
|
a0ee9a7a8a
|
Rename apply-lora arg
|
2024-09-05 21:50:31 +02:00 |
|
Fabio
|
0a2f21af5a
|
fix widht <-> height bug
|
2024-09-05 20:06:59 +02:00 |
|
filipstrand
|
96848e320f
|
Add support for multiple LoRAs again
|
2024-09-05 19:54:46 +02:00 |
|
filipstrand
|
ff9f998638
|
Small fixes
|
2024-09-04 23:16:02 +02:00 |
|
Filip Strand
|
d5f5f9607e
|
Fix type
Co-authored-by: Fabio Peruzzo <39661245+Xuzzo@users.noreply.github.com>
|
2024-09-04 23:14:38 +02:00 |
|
filipstrand
|
f28fffe0cf
|
Point out the .safetensors file again
|
2024-09-04 22:44:11 +02:00 |
|
filipstrand
|
a3567bddd7
|
Start supporting only single LoRA (and some other simplifications)
|
2024-09-04 22:15:03 +02:00 |
|
filipstrand
|
6d35db5e9a
|
Use mx.load instead of safe_open
|
2024-09-04 21:05:19 +02:00 |
|
filipstrand
|
5ad5352481
|
Introduce weight util for shared methods
|
2024-09-04 20:20:27 +02:00 |
|
filipstrand
|
af41b08d90
|
Move LoRA related things to a LoraUtil (have to think about where to best place this later...)
|
2024-09-04 20:10:45 +02:00 |
|
filipstrand
|
8983070728
|
Code style improvements and some restructuring
|
2024-09-04 20:10:45 +02:00 |
|
Filip Strand
|
b4c27a6fab
|
raise error if layer cannot be loaded
Co-authored-by: Fabio Peruzzo <39661245+Xuzzo@users.noreply.github.com>
|
2024-09-04 19:43:32 +02:00 |
|
elitexp
|
0fd03c7552
|
@Xuzzo - Weight Adjustment as Original Transformer
Co-authored-by: Fabio Peruzzo <39661245+Xuzzo@users.noreply.github.com>
|
2024-09-04 21:52:51 +05:45 |
|
Sujip Maharjan
|
8d8812675e
|
feat: --apply-lora a.safetensors b.safetensors c.safetensor --lora-scales 0.5 1.0 0.5
|
2024-09-03 19:36:15 +05:45 |
|
Sujip Maharjan
|
03b929e732
|
feat: Add --lora-scale parameter to adjust the scaling of LoRA weights
|
2024-09-03 18:39:01 +05:45 |
|
elitexp
|
4dfb3aa892
|
Clean up weight handler
@xuzzo Cleanup code
Co-authored-by: Fabio Peruzzo <39661245+Xuzzo@users.noreply.github.com>
|
2024-09-03 18:19:21 +05:45 |
|
Sujip Maharjan
|
f82caa3298
|
Icrecream dependency removed, not required -- error
|
2024-09-03 13:16:35 +05:45 |
|
Sujip Maharjan
|
cd54ad137c
|
Apply lora with --apply-lora <path-to-safetensors>
|
2024-09-03 07:38:04 +05:45 |
|
Filip Strand
|
94920896e8
|
Merge pull request #24 from filipstrand/basic-quantization-support
Basic quantization support
|
2024-08-30 22:24:05 +02:00 |
|