Giters
mosaicml
/
diffusion
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
650
Watchers:
15
Issues:
58
Forks:
64
mosaicml/diffusion Issues
Is this dataset still expected to be released?
Closed
2 months ago
Comments count
4
When is common canvas going to be released?
Closed
2 months ago
Comments count
23
ERROR:composer.cli.launcher:Rank 0 crashed with exit code -11.
Closed
3 months ago
Comments count
1
Implementing Mosaic Diffusion into Patch-Diffusion
Updated
5 months ago
Training a MosaicML
Updated
5 months ago
Example config for training VAE
Updated
6 months ago
Comments count
4
TypeError("'NoneType' object is not iterable")
Closed
6 months ago
Comments count
1
Multi-node training
Closed
7 months ago
How to do continue training when a job failed
Updated
7 months ago
Comments count
1
Convert Pt model to safetensor
Closed
7 months ago
Forward order differs across ranks: rank 0 is all-gathering 1 parameters while rank 4 is all-gathering -2142209024 parameters
Updated
7 months ago
Comments count
2
What is the benefit of multi phase training?
Closed
8 months ago
Comments count
2
Training with modest data
Closed
8 months ago
Comments count
1
FID from the mainline code is different from https://github.com/mosaicml/diffusion/tree/ejyuen-patch-1
Updated
8 months ago
Comments count
1
How can I solve this problem?
Closed
a year ago
Error when training with local precomputed features
Updated
9 months ago
Comments count
3
[dynamo] `UnspecializedNNModuleVariable` does not implement object identity
Closed
9 months ago
Comments count
1
FID and CLIP score
Closed
9 months ago
Comments count
5
FID score changes a lot during the model training
Updated
9 months ago
Comments count
2
Bug report: ValueError: invalid literal for int() with base 10: '/tmp/mds-cache/mds-coco-2014-val-fid-clip-17'
Updated
9 months ago
upsample_nearest_nhwc only supports output tensors with less than int_max
Closed
9 months ago
Comments count
7
FID score is weird
Closed
9 months ago
Comments count
3
Any plan to support "Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack"?
Closed
9 months ago
Comments count
2
train error during evaluation with 1 GPU and train with multi GPU
Updated
9 months ago
Comments count
2
An error occurred while running laion_cloudwriter.py
Closed
9 months ago
Bug Report of image_caption.py
Closed
9 months ago
Comments count
1
Compare latents from training code and latents from precompute_latents.py
Closed
9 months ago
Comments count
1
NaN loss and Watchdog timeout error caused by _accumulate_time_across_ranks
Closed
9 months ago
Comments count
1
How can I improve to solve this problem?
Closed
10 months ago
Comments count
10
Why do we load clip-vit-large-patch14?
Closed
10 months ago
Comments count
9
Grad become NaN
Updated
a year ago
Comments count
3
can we use coco_captions dataset to train your model???
Closed
a year ago
Comments count
2
fp32
Updated
a year ago
Comments count
1
H100 support issue
Closed
a year ago
Comments count
4
Are you planning releasing the trained model?
Closed
a year ago
Comments count
3
Error doing composer run.py --config-path yamls/hydra-yamls --config-name SD-2-base-512.yaml
Updated
a year ago
Comments count
4
ValueError('cannot mmap an empty file')
Updated
a year ago
Comments count
1
Could this code be used for 3090ti
Closed
a year ago
Comments count
1
leaked shared_memory
Updated
a year ago
Comments count
1
save_overwrite conflicts with autoresume=true
Closed
a year ago
Comments count
1
Training verbose logs
Updated
a year ago
Comments count
3
Setting for used gpus
Closed
a year ago
Comments count
1
Throughput is low
Closed
a year ago
Comments count
4
MissingEnvironmentError: Torch distributed is initialized but environment variable NODE_RANK is not set.
Closed
a year ago
Comments count
7
Missing/Unexpected Keys when load a checkpoint
Closed
a year ago
Comments count
3
NaN loss after 6K steps with batch size 2048
Closed
a year ago
Comments count
5
Why are you using COCO2014 to calculate FID and CLIP score
Closed
a year ago
How long does it take to run laion_cloudwriter.py and precompute_latents.py for aesthetic-4.5
Closed
a year ago
Comments count
1
A question regarding the lr scheduler
Closed
a year ago
Comments count
8
No initialize_dist in precompute_latent.py
Closed
a year ago
Comments count
2
Previous
Next