-
Notifications
You must be signed in to change notification settings - Fork 5.4k
Issues: huggingface/diffusers
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Why isn’t VRAM being released after training LoRA?
bug
Something isn't working
#9876
opened Nov 6, 2024 by
hjw-0909
FluxInpaintPipeline overrides pixels outside the mask
bug
Something isn't working
#9867
opened Nov 5, 2024 by
Clement-Lelievre
Flux controlnet can't be trained, do this script really work?
bug
Something isn't working
#9866
opened Nov 5, 2024 by
liuyu19970607
Flux training seems not to update the transformer model
bug
Something isn't working
#9861
opened Nov 4, 2024 by
weixiong-ur
ConnectionError: Tried to launch distributed communication on port 29401, but another process is utilizing it. Please specify a different port (such as using the --main_process_port flag or specifying a different main_process_port in your config file) and rerun your script. To automatically use the next open port (on a single node), you can set this to 0.
bug
Something isn't working
#9856
opened Nov 4, 2024 by
qinchangchang
make gradient checkpointing with frozen model possible
bug
Something isn't working
#9850
opened Nov 3, 2024 by
MikeTkachuk
FluxControlNetModel got not from_single_file()? It's really necessary.
bug
Something isn't working
#9846
opened Nov 2, 2024 by
riflemanl
[TypeError] in DreamBooth SDXL LoRA training when Something isn't working
use_dora
parameter is False
bug
#9841
opened Nov 2, 2024 by
adhiiisetiawan
Loading SDXL loras into Flux
bug
Something isn't working
#9822
opened Oct 31, 2024 by
christopher5106
prepare_ip_adapter_image_embeds
Bug Causes Feature Mixing During Batch Processing in IP-Adapter
bug
#9813
opened Oct 30, 2024 by
heiheizwplus
Lora does not support module_to_save()
bug
Something isn't working
#9810
opened Oct 30, 2024 by
liuchaohu
FLUX.1-dev dreambooth training problem on multigpu
bug
Something isn't working
#9790
opened Oct 29, 2024 by
jyy-1998
With examples/dreambooth /README_flux.md guide setting up and training, got cuda OOM with 3090Ti 24GB
bug
Something isn't working
#9732
opened Oct 21, 2024 by
riflemanl
How to use Playground2.5 to train lora with own dataset to generate pictures of a specific style?
bug
Something isn't working
#9731
opened Oct 21, 2024 by
hjw-0909
RuntimeError: cuDNN Frontend error: [cudnn_frontend] Error: No execution plans support the graph.
bug
Something isn't working
#9704
opened Oct 17, 2024 by
alansmithee-cpu
[SD3 ControlNet] bug in pipeline 'controlnet_pooled_projections'
bug
Something isn't working
#9686
opened Oct 15, 2024 by
tobiasfshr
Error in loading flux fp8 model with local transformer_flux.py file
bug
Something isn't working
#9667
opened Oct 14, 2024 by
DhavalTaunk08
The from_pretrained method of the DiffusionPipeline doesn't set the passed modules' mode to evaluation.
bug
Something isn't working
#9660
opened Oct 12, 2024 by
wtyuan96
Code With Strange Logic in CogVideoX's Dynamic CFG
bug
Something isn't working
#9641
opened Oct 11, 2024 by
immortalCO
XFormer fails when passing attention mask while using bfloat and key's sequence length not being a multiple of 8
bug
Something isn't working
#9637
opened Oct 10, 2024 by
dhmbb2
Error when setting num_single_layers=0 while training flux-controlnet on a multi-GPU server using a single GPU
bug
Something isn't working
#9630
opened Oct 9, 2024 by
wangherr
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.