-
Todo List
- [x] enlarge hidden size
- [x] look into the implementation
- [ ] Check Jason T2T code
- [ ] Steal Jason's T2T dataset (perhaps his dataset is better )
- [x] weight average ?
Che…
zomux updated
4 years ago
-
### 🐛 Describe the bug
```shell
Reason: Illegal getattr invocation stride in strict mode
```
I have a kernel which requires strides.
but when I access the stride inside a torch.autograd.Functio…
-
What a great job. When i use A800 80G with default parameters to infer the 768P video, I find that the GPU memory increases first and then decreases. The step inference is fine, but an OOM error is re…
-
bf16 is very helpful to solve the black image generated by vae. There is a related implementation [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9295), but it cannot take effect o…
-
Thank you to all the contributors for their contributions that have allowed me to experience such an interesting package. I have developed an application that can run ml-stable-diffusion smoothly on i…
-
Running VAEs and CLIP/T5 embedders is time expensive, and this cost scales up fast when multiple trainings are re-run.
As we keep these parts frozen and train only the diffusion model, we can decide …
-
Hi, I couldn't find the implementation for latent posteriors of q(yl | X) and q(zl | X) as discussed in the claimed paper. The MC estimate of the variational lower bound also seems to be missing as di…
-
I'm unsure of the role the pseudo inputs play in generation using a Vamp Propr. This is likey my lack of understanding of your paper because I find it hard to reconcile these implementation details wi…
-
### Summary
# Motivation
WasmEdge runtime provides inference support for AI models and LLMs (large language models, such as llama3 and phi-3-mini). Stable Diffusion is a popular category that we…
-
the latent_channels in `scripts/vae/sevirlr/cfg.yaml` is 64 but the latent_channels in the paper's Implementation Details is 4.
Will it reduce the training time during the denoise when the latent_ch…