universe
universe
@htoyryla That's inspiring. Thank u.
@htoyryla can u make your dataset and pretrained models' parameters available?
I got the same problem when read the my own training model, any help here? The lua script result is different from opencv result for my own training model.However, the...
I referred to the 'retrain.py' and solved this problem by using 'bottleneckinput' placehoder instead. @didiwai The retrain.py link: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py
> Yes. You can load your ckpt into DeForum, or a similar batch img2img colab. If i use dreambooth this way, what is the difference between dreambooth and the stable...
Same problem here。 I train controlnet with 1 batchsize， and got cuda out of memory error with 80g vram
> Are you using 1B or 3.6B? That will make a difference (though still pretty hefty). changed to 1B model， still cuda out of memory ...
> 1. Run training script with torchrun instead of srun > (e.g., torchrun --standalone --nnodes 1 --nproc_per_node 2 train/~~~~) > 2. Exchange SLURM_LOCALID, SLURM_PROCID, SLURM_NNODES to LOCAL_RANK, RANK, WORLD_SIZE in...
> Hi, this issue has been fixed in recent `diffusers` versions, which allows `safety_checker=None`, could you please update your diffusers version `pip install -U diffusers`. That should fix it. Still...
> Hello I've found some problems it`s Before Make Classes, After Finish train > > If make Classes Image > > ``` > The following values were not passed to...