apple ml-mdm issues - Githubissues

apple / ml-mdm

Train high-quality text-to-image diffusion models in a data & compute efficient manner

https://machinelearning.apple.com/research/matryoshka-diffusion-models

MIT License

443 stars 30 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Use a quantized LM or something smaller to make it easier to run the demo

#47 luke-carlson opened 23 minutes ago
0
Convert all argparse arguments to data classes + simple parsing

#46 luke-carlson opened 42 minutes ago
0
Assist in creating MLX implementations of UNet, NestedUnet, etc

#45 luke-carlson opened 43 minutes ago
0
README updates

#44 pedroborgescruz opened 17 hours ago
0
changed token_file to vocab_file for consistency

#43 aaliyahnl closed 36 minutes ago
0
Update generate_sample.py (matplotlib use Agg backend)

#42 levinkhho closed 38 minutes ago
0
Tests for tokenizer.py

#41 pedroborgescruz opened 5 days ago
0
Create separate dependency lists for cpu vs gpu, eg "pip install .[cpu]" vs "pip install .[gpu]"

#40 luke-carlson opened 6 days ago
0
Switch the default `pytest` call to run just CPU test cases

#39 luke-carlson opened 6 days ago
1
Separate python dependencies into optional groups

#38 luke-carlson opened 6 days ago
1
renaming instances of token_file to vocab_file

#37 aaliyahnl opened 1 week ago
1
Web demo fails if generation is stopped before completion

#36 levinkhho opened 1 week ago
1
Update torch requirement >=2.5.1 pyproject.toml

#35 levinkhho closed 37 minutes ago
0
Potential update to pyproject.toml to get web demos to run?

#34 emmagarr opened 1 week ago
1
Type hints for train_batch

#33 emmagarr closed 36 minutes ago
0
Add short tutorials on the steps needed to add a new model/tokenizer/ or language model

#32 luke-carlson opened 1 week ago
1
Update the README with more details about what specific files do

#31 luke-carlson opened 1 week ago
2
add type hinting to any file that needs it

#30 luke-carlson opened 1 week ago
1
Making train_parallel.py work on a single machine (non-distributed)

#29 levinkhho opened 1 week ago
0
Add doc strings to testcases (25)

#28 bdeanhardt closed 1 week ago
3
Create test cases for the Tokenizer

#27 luke-carlson opened 3 weeks ago
4
Add information to the readme explaining what MODEL_REGISTRY, PIPELINE_REGISTRY, etc all do

#26 luke-carlson opened 3 weeks ago
1
Add doc strings to testcases

#25 luke-carlson opened 3 weeks ago
1
Add type hinting to train_batch function

#24 luke-carlson opened 3 weeks ago
2
Use default_factory for mutable fields

#23 luke-carlson closed 2 weeks ago
6
Request for kindly releasing ImageNet models.

#22 chandramouli-sastry opened 1 month ago
0
Fix config loading bugs for MDM models, adding one missing config

#21 MultiPath closed 1 month ago
0
if I incerease step size more than 50, 256x256 model does not work.

#20 Oguzhanercan closed 1 month ago
2
README console highlighting

#19 luke-carlson closed 1 month ago
0
Fix some small things

#18 tolgacangoz closed 5 days ago
2
Refactor `samplers.py` to correctly handle scaling when `config.schedule_shifted` is `True`

#17 tolgacangoz closed 1 month ago
0
Update `generate_sample.py`

#16 tolgacangoz closed 1 month ago
0
Fix issue with vision model download and module mimicry

#15 tolgacangoz closed 1 month ago
0
Proposes to refactor `diffusion.py` for `if not self.diffusion_config.no_use_residual:`

#14 tolgacangoz closed 5 days ago
0
Update `cc12m_256x256.yaml` with diffusion_config addition and use `null` as a correct version of `None`

#13 tolgacangoz closed 1 month ago
0
Fix a typo in `README.md`

#12 tolgacangoz closed 2 months ago
3
web_ui 运行报错

#11 fallbernana123456 opened 3 months ago
0
both 256,1024 model got AttributeError: 'NestedDiffusionConfig' object has no attribute 'mixed_batch'. Did you mean: 'mixed_ratio'?

#10 PengceWang opened 3 months ago
0
Fix typo in cc12m_256x256.yaml

#9 pcuenca closed 2 months ago
0
Find packages on setup

#8 pcuenca closed 2 months ago
0
Support Runtime on Apple Silicon

#7 SCAuFish closed 3 weeks ago
0
Not found the library: distributed

#6 alfredplpl opened 3 months ago
5
need colab, hf spaces, or replicate demo

#5 s9anus98a opened 3 months ago
3
[Question] Training another layer

#4 Sys-if closed 3 months ago
1
[question] inference speed comparison?

#3 eisneim opened 3 months ago
0
Web demo link is broken

#2 rupeshs closed 3 months ago
1
Fix broken web demo link in readme

#1 rupeshs closed 3 months ago
1