monster/Qwen-Image-Layered-MRP-MLX
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README with perf. update, installation issue and version link

Browse Source
This commit is contained in:
filipstrand 2024-12-26 20:50:38 +01:00
parent 2ebb0d1c6e
commit 0eb8f5082e
1 changed files with 18 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
README.md
View File

@ -121,6 +121,8 @@ pip install -U mflux
</details>
*If you have trouble installing MFLUX, please see the [installation related issues section](https://github.com/filipstrand/mflux/issues?q=is%3Aissue+install+).*
### 🖼️ Generating an image
Run the command `mflux-generate` by specifying a prompt and the model and some optional arguments. For example, here we use a quantized version of the `schnell` model for 2 steps:
@ -301,20 +303,21 @@ To find out the spec of your machine (including number of CPU cores, GPU cores,
system_profiler SPHardwareDataType SPDisplaysDataType
```
| Device | M-series | User | Reported Time | Notes |
|-------------|---------------------|-----------------------------------------------------------------------------------------------------------------------------------|---------------|---------------------------|
| Mac Studio | 2023 M2 Ultra | [@awni](https://x.com/awnihannun/status/1823515121827897385) | <15s | |
| Macbook Pro | 2024 M4 Max (128GB) | [@ivanfioravanti](https://gist.github.com/awni/a67d16d50f0f492d94a10418e0592bde?permalink_comment_id=5153531#gistcomment-5153531) | ~19s | |
| Macbook Pro | 2023 M3 Max | [@karpathy](https://gist.github.com/awni/a67d16d50f0f492d94a10418e0592bde?permalink_comment_id=5153531#gistcomment-5153531) | ~20s | |
| - | 2023 M2 Max (96GB) | [@explorigin](https://github.com/filipstrand/mflux/issues/6) | ~25s | |
| Mac Mini | 2024 M4 Pro (64GB) | [@Stoobs](https://github.com/filipstrand/mflux/issues/92) | ~34s | |
| Mac Mini | 2023 M2 Pro (32GB) | [@leekichko](https://github.com/filipstrand/mflux/issues/85) | ~54s | |
| - | 2022 M1 MAX (64GB) | [@BosseParra](https://x.com/BosseParra/status/1826191780812877968) | ~55s | |
| Macbook Pro | 2023 M2 Max (32GB) | @filipstrand | ~70s | |
| - | 2023 M3 Pro (36GB) | [@kush-gupt](https://github.com/filipstrand/mflux/issues/11) | ~80s | |
| Macbook Pro | 2021 M1 Pro (32GB) | @filipstrand | ~160s | |
| - | 2021 M1 Pro (16GB) | [@qw-in](https://github.com/filipstrand/mflux/issues/7) | ~175s | Might freeze your mac |
| Macbook Air | 2020 M1 (8GB) | [@mbvillaverde](https://github.com/filipstrand/mflux/issues/13) | ~335s | With resolution 512 x 512 |
| Device | M-series | User | Reported Time | Notes |
|-------------|---------------------|------------------------------------------------------------------------------------------------------------------------------------|---------------|---------------------------------|
| Mac Studio | 2023 M2 Ultra | [@awni](https://x.com/awnihannun/status/1823515121827897385) | <15s | |
| Macbook Pro | 2024 M4 Max (128GB) | [@ivanfioravanti](https://gist.github.com/awni/a67d16d50f0f492d94a10418e0592bde?permalink_comment_id=5153531#gistcomment-5153531) | ~19s | |
| Macbook Pro | 2023 M3 Max | [@karpathy](https://gist.github.com/awni/a67d16d50f0f492d94a10418e0592bde?permalink_comment_id=5153531#gistcomment-5153531) | ~20s | |
| - | 2023 M2 Max (96GB) | [@explorigin](https://github.com/filipstrand/mflux/issues/6) | ~25s | |
| Mac Mini | 2024 M4 Pro (64GB) | [@Stoobs](https://github.com/filipstrand/mflux/issues/92) | ~34s | |
| Mac Mini | 2023 M2 Pro (32GB) | [@leekichko](https://github.com/filipstrand/mflux/issues/85) | ~54s | |
| - | 2022 M1 MAX (64GB) | [@BosseParra](https://x.com/BosseParra/status/1826191780812877968) | ~55s | |
| Macbook Pro | 2023 M2 Max (32GB) | @filipstrand | ~70s | |
| - | 2023 M3 Pro (36GB) | [@kush-gupt](https://github.com/filipstrand/mflux/issues/11) | ~80s | |
| Mac Mini | 2024 M4 (16GB) | [@wnma3mz](https://github.com/filipstrand/mflux/issues/105) | ~97s | 512 x 512, 8-bit quantization |
| Macbook Pro | 2021 M1 Pro (32GB) | @filipstrand | ~160s | |
| - | 2021 M1 Pro (16GB) | [@qw-in](https://github.com/filipstrand/mflux/issues/7) | ~175s | Might freeze your mac |
| Macbook Air | 2020 M1 (8GB) | [@mbvillaverde](https://github.com/filipstrand/mflux/issues/13) | ~335s | With resolution 512 x 512 |
*Note that these numbers includes starting the application from scratch, which means doing model i/o, setting/quantizing weights etc.
@ -597,7 +600,7 @@ To report additional formats, examples or other any suggestions related to LoRA
### 🎛 Dreambooth fine-tuning
As of release 5.0, MFLUX has support for fine-tuning your own LoRA adapters using the [Dreambooth](https://dreambooth.github.io) technique.
As of release [v.0.5.0](https://github.com/filipstrand/mflux/releases/tag/v.0.5.0), MFLUX has support for fine-tuning your own LoRA adapters using the [Dreambooth](https://dreambooth.github.io) technique.
![image](src/mflux/assets/dreambooth.jpg)