ExponentialML / Text-To-Video-Finetuning

Finetune ModelScope's Text To Video model using Diffusers 🧨

ExponentialML/Text-To-Video-Finetuning Issues

init_video problem
Updated 6 months ago
TypeError: Linear.forward() got an unexpected keyword argument 'scale'
Updated 7 months ago6
ControlNet
Updated 7 months ago
Normal finetuning instead of LoRA
Updated 7 months ago
About step_loss of version2
Closed a year ago4
issues on train.py
Updated 7 months ago1
Lora on ResnetBlock2D in modelscope model
Closed 7 months ago1
Can the videocomposer model be adapted to this training framework?
Updated 8 months ago
wrong norm method
Closed 8 months ago1
Two forward passes in finetune_unet
Updated 8 months ago1
[inference] latents_window index error
Closed 8 months ago1
Enabling Multi-GPU training
Updated 9 months ago3
Lora inference problem
Updated 9 months ago7
A typo
Updated 9 months ago
AttributeError: 'Tensor' object has no attribute 'config'
Closed 10 months ago5
How can I run the fine-tuning on a GPU with <= 16GB of VRAM?
Closed 10 months ago3
I have some doubts about the framework
Closed 10 months ago4
RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1, 1, 512] because the unspecified dimension size -1 can be any value and is ambiguous
Closed 10 months ago3
Does this code support native finetune for damo text to video model?
Closed 10 months ago2
Which paper?
Closed 10 months ago1
How to train with folder video
Closed 10 months ago1
webui Lora Might be causing errors in checkpoint models.
Updated a year ago3
How to test my model
Updated a year ago9
finetune train error of "UnboundLocalError: local variable 'use_offset_noise' referenced before assignment"
Closed a year ago2
error of "from accelerate.logging import get_logger"
Closed a year ago2
Transformer2D initializing
Updated a year ago1
training video
Updated a year ago
TypeError: UNet3DConditionModel._set_gradient_checkpointing() got multiple values for argument 'value'
Closed a year ago3
How much VRAM do I need for saving the weights?
Closed a year ago4
Refer to the official release of Diffusers?
Closed a year ago2
similar implementation to Nivida VideoLDM?
Updated a year ago5
Accelerator 'function' object has no attribute '__func__'
Closed a year ago3
Question: regarding fine-tuning with images
Closed a year ago1
About VideoLDM
Updated a year ago7
Feature request
Updated a year ago9
Encountered 2 file(s) that may not have been copied correctly on Windows
Closed a year ago1
Default model seems to output only noise or greenscreen
Updated a year ago6
First GPU occupies more VRAM in distributed training
Updated a year ago
inference code generate only green noise
Updated a year ago1
Links to weights?
Closed a year ago1
about vid2vid in inference
Closed a year ago1
Error with inference
Closed a year ago2
NameError: name 'glob' is not defined
Closed a year ago40
model inference of version2
Closed a year ago7
Main ways to avoid overfitting?
Closed a year ago1
Whats the deal with train_text_encoder: ?
Closed a year ago1
Is there a problem with attn3 here?
Closed a year ago1
How does n_sample_frames: work?
Closed a year ago1
Question about finetuning multiple videos, each one with a different prompt, using the video_folder.yaml
Closed a year ago2
How do you turn off validation?
Closed a year ago1