openai / consistency_models

Official repo for consistency models.

openai/consistency_models Issues

Is there a non-stochastic sampling method?
Updated 2 months ago1
Why use teacher model in Consistency training
Closed 4 months ago5
pip install -e . error
Closed a year ago2
Issue with `use_fp16=True` Leading to Type Conversion Error in `unet.py`
Updated 3 months ago1
cannot import name '_get_cpp_backtrace' from 'torch._C'请问这种问题该怎样解决呢
Updated 4 months ago2
ModuleNotFoundError: No module named 'cm'
Updated 4 months ago3
The difference between Loss( f(x0+t_{n+1}*z) , f(x0+t_{n}*z) ) and Loss( f(x0+t_{n+1}*z), x0 )?
Updated 5 months ago4
An module error when running cm_train.py
Updated 5 months ago1
Is the sampling reversible? (Image to Noise)
Updated 5 months ago3
Can I use the checkpoint provided by the original EDM paper to train the consistency model?
Updated 5 months ago
Training settings and pretrained models for CIFAR-10
Updated 6 months ago4
Why does the training not stop？
Updated 6 months ago
GPU Training Time for CD and CT Models on ImageNet64X64?
Updated 7 months ago
Request for unconditional model on ImageNet 64*64
Updated 7 months ago
How to implement on stable diffusion?
Updated 7 months ago3
Code for Zero-Shot Image Editing
Updated 7 months ago7
[inpainting] wrong shape?
Updated 7 months ago
where can we get the ref_batches/imagenet64.npz file for FID evaluation
Closed 7 months ago1
When and where the repository for CIFAR-10 experiments release?
Updated 7 months ago1
“multi-gpu error” dist.all_gather(gathered_samples, sample) # gather not supported with NCCL
Updated 8 months ago1
RuntimeError: FlashAttention is only supported on CUDA 11 and above
Closed 8 months ago8
Different batches size while training
Updated 9 months ago
RuntimeError in the sample `diffusers` code in README.md
Closed 9 months ago2
Sampling with Diffusers
Updated 10 months ago1
The parameter sigma_data for KarrasDenoiser.
Updated 10 months ago
Suffering problem when installing dependence using pip install -e . on google colab
Updated 10 months ago2
torch version
Updated 10 months ago5
Not able to obtain results like the checkpoint models (CT, imagenet64) when trying to train from scratch
Updated a year ago1
Is there any consistency model on face dataset?
Updated a year ago1
Description The sampling command blocked
Updated a year ago1
QKVFlashAttention unexpected parameters error, running in Google Colab
Closed a year ago21
Super-resolution conditional training
Updated a year ago3
I use the pre-trained model to generate pictures, the effect is too bad, I don't know what's going on.
Updated a year ago9
implement a non-Cuda flash attention module
Updated a year ago1
I wonder how to train my own datasets based on your models
Updated a year ago10
An error was reported while running the project：
Updated a year ago1
Use one gpu to generate images using a pretrained model without the communication protocol nccl.
Updated a year ago25
CUDA out of memory
Updated a year ago1
question about running scripts: time out initializing process group
Closed a year ago3
why lg_loss_scale？
Updated a year ago
Specifying a specific image as supervisory information for the generated image？
Updated a year ago1
Evaluation: Reference Batches for CIFAR10
Updated a year ago1
How to visualize samples stored by np?
Updated a year ago4
How to run on a single linux server with multiple GPUs
Updated a year ago12
Differences between code and paper
Updated a year ago2
Multistep sampling in Algorithm 1
Updated a year ago1
Inconsistent loss term with paper
Updated a year ago6