Arslan Artykov comments

Results 10 comments of


                                            Arslan Artykov

Reprojected loss function

@iariav, @Wenchao-Du, @VitorGuizilini-TRI I've implemented the Reprojected Distance Loss function and pull requested. Hopefully, it will satisfy your needs. Best regards!

Unable to build docker image

Hey @rashikshrestha, sorrry for the late reply. I made some changes in the docker file in order to adapt the library versions according to my GPU type and etc. After...

When is the training and inference code going to be released?

Hey, @huanglianghua congrats on the great work. Currently, I am trying to implement the paper onto the stable diffusion. My question is, what does the following sentence mean; "Project image...

When is the training and inference code going to be released?

Hey @huanglianghua! Thanks for your feedback! And I also similarly projected text embeddings to a shape of (B, 77*768) and added it to timestep embedding of shape (B, 4 *...

When is the training and inference code going to be released?

Dear all, I am excited to announce that I have begun implementing a lightweight Latent Composer based on the stable diffusion model. I have already completed the majority of the...

When is the training and inference code going to be released?

> > Dear everyone, > > I wanted to take a moment to provide an update on our plans for Composer's open source release. We have been working hard to...

When is the training and inference code going to be released?

> > > > Dear everyone, > > > > I wanted to take a moment to provide an update on our plans for Composer's open source release. We have...

When is the training and inference code going to be released?

> Dear all, > > I am excited to announce that I have begun implementing a lightweight Latent Composer based on the stable diffusion model. I have already completed the...

Very little movement with mm_sd_v15.ckpt?

It should generate 2 different outputs, one with fast movement and another with a slow one. At least, it is so in my case.

huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'models/StableDiffusion/stable-diffusion-v1-5'. Use `repo_type` argument if needed.

Try setting "parser.add_argument("--pretrained_model_path", type=str, default="models/StableDiffusion/stable-diffusion-v1-5.safetensors",) " default path to "models/StableDiffusion". It should solve your problem.