Weird image when running the sample generator

[metatl]

Just installed and give it a test of the trained model.

from tld.configs import LTDConfig, DenoiserConfig, TrainConfig
from tld.diffusion import DiffusionTransformer

denoiser_cfg = DenoiserConfig(n_channels=4) #configure your model here.
cfg = LTDConfig(denoiser_cfg=denoiser_cfg)

diffusion_transformer = DiffusionTransformer(cfg)

out = diffusion_transformer.generate_image_from_text(prompt="a cute cat")
I got something like this:

Not sure why.

[apapiu]

Hey @metatl, try using the legacy_dh_order branch - the model was trained with a small but annoying difference in ordering of the hidden dimensions and head dimensions and unfortunately I haven't found a simple way to fix that. Let me know if that doesn't work.

[huangxiancun]

Just installed and give it a test of the trained model.

from tld.configs import LTDConfig, DenoiserConfig, TrainConfig from tld.diffusion import DiffusionTransformer

denoiser_cfg = DenoiserConfig(n_channels=4) #configure your model here. cfg = LTDConfig(denoiser_cfg=denoiser_cfg)

diffusion_transformer = DiffusionTransformer(cfg)

out = diffusion_transformer.generate_image_from_text(prompt="a cute cat") I got something like this:

Not sure why.

hello i meet this too,pls,can you solve this problem?

[huangxiancun]

Hey @metatl, try using the legacy_dh_order branch - the model was trained with a small but annoying difference in ordering of the hidden dimensions and head dimensions and unfortunately I haven't found a simple way to fix that. Let me know if that doesn't work.

hi ,your project help me bigger, i try trainning in 4090ti ，it is too slow, how to quickly? for example how to distributed training in this accelerator famework,i just see it in one gpu.