Text-To-Video-Finetuning

Text-To-Video-Finetuning copied to clipboard

when running inference with an init_video, runtime error happen. timesteps = timesteps[0] (inference.py line194) → for timestep in timesteps(diffusers/schedulers/scheduling_dpmsolver_multistep.py line900) This error, "iteration over a 0-d tensor," occurs when attempting...

Yuuki-00

Evals

2

added CLIP and FID evals and interval and random frame sampling.

masoudcharkhabi

TypeError: Linear.forward() got an unexpected keyword argument 'scale'

6

Hi, I have been trying to do fine-tuning with stable LoRA, according to the manual. I only can do the basics, so I haven't modified the stable_lora_config.yaml other than the...

kenkenissocool

Are there any plans to add ControlNet? Or is it possible to use this model with ControlNet Pipeline from diffusers?

julkaztwittera

Is there a way I can set the train config to do a normal finetuning on a large dataset instead of LoRA?

julkaztwittera

issues on train.py

1

please help me  

MuhammadNaeem42

https://github.com/damo-vilab/videocomposer Modelscope and videocomposer both seem to come from Alibaba.

YujieOuO

Two forward passes in finetune_unet

1

Hey, thanks for open-sourcing this code! I had a quick question about the `finetune_unet` function in `train.py`: why are there two forward passes and loss computations through the unet? Is...

gunshi

Enabling Multi-GPU training

3

How to enable multi-GPU training? No matter how many GPUs I use, only one process starts.

julkaztwittera

Lora inference problem

7

When trying to run inference using --lora_path parameter, getting : ``` LoRA rank 64 is too large. setting to: 4 list index out of range Couldn't inject LoRA's due to...

zacaikido