TokenFlow

TokenFlow copied to clipboard

Thanks for your owesome work. In run_tokenflow_pnp.py, why using "noisy_latents = self.scheduler.add_noise(self.latents, self.eps, self.scheduler.timesteps[0])" line257 before "edited_frames = self.sample_loop(noisy_latents, torch.arange(self.config["n_frames"]))" line 258. It seems directly using "edited_frames = self.sample_loop(noisy_latents, torch.arange(self.config["n_frames"]))"...

LiuRicky

Is it all code released?

1

Hi, thanks for great work! But, I can't find 'compute nn fields' and 'tokenflow propagation' it just looks using PnP instead. Is this repo is not implemented with original tokenflow...

hyoseok1223

a problem about the code,thanks

3

it seems that you change all the basictransformerblock in both down_blocks, mid_blocks and up_blocks. why still change the up_blocks in the unet again? ```python def register_extended_attention(model): for _, module in...

aosong01

not compatible with diffusers 0.21+ [with workaround]

2

everything runs ok on diffusers version 0.20 or below, while getting this error on diffusers 0.21: ``` File "F:\_neuro\SDfu\lib\tokenflow.py", line 185, in denoise_step noise_pred = self.unet(lat_in, t, conds).sample File "C:\Users\eps\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\modules\module.py",...

eps696

when run python run_tokenflow_pnp.py Traceback (most recent call last): File "/mnt/disk_1/kaizhou/TokenFlow/run_tokenflow_pnp.py", line 300, in run(config) File "/mnt/disk_1/kaizhou/TokenFlow/run_tokenflow_pnp.py", line 279, in run editor = TokenFlow(config) File "/mnt/disk_1/kaizhou/TokenFlow/run_tokenflow_pnp.py", line 62, in __init__...

kzl787

``` (tokenflow) C:\tut\TokenFlow>python preprocess.py --data_path data/woman-running.mp4 --inversion_prompt "a silver sculpt ure of a woman running" A matching Triton is not available, some optimizations will not be enabled Traceback (most recent...

nitinmukesh

ValueError: attempt to get argmax of an empty sequence

1

Any suggestions how to fix this issue I am using the default provided with the repository, only updated the following in \TokenFlow\configs\config_pnp.yaml 1. batch_size: 8 to batch_size: 1 2. data_path:...

nitinmukesh

"ValueError: max() arg is an empty sequence" when trying to run via jupyterlab env

1

I'm trying to tokenflow via jupyterlab env. On the last step, when running `run_tokenflow_pnp.py`, I get this error: ``` Traceback (most recent call last): File "/home/jovyan/token-flow/run_tokenflow_pnp.py", line 301, in run(config)...

bstnhnsl

SD XL Integration

1

Is it possible to integrate the latest SD XL to the stable diffuion option?

irvansian

Adapt to use SDD-1B?

1

https://huggingface.co/segmind/SSD-1B or https://github.com/luosiallen/latent-consistency-model

G-force78