tianweiy / DMD2

tianweiy/DMD2 Issues

Generating VAE latents for a different architecture
Closed 13 days ago4
set model to train mode
Closed 16 days ago8
Convert 4-step unet into a checkpoint file
Updated 21 days ago6
Please tell me where is the data files: sdxl_vae_latents_laion_500k_lmdb? I can not find it.
Closed a month ago1
request default -1 seed and negative prompt
Closed a month ago2
a Lora version to add to any Community Models?
Updated a month ago6
How about DMD2 on img2img task?
Updated a month ago2
When i train SDXL-4steps model, i get OOM error, i use a single A100.
Closed a month ago2
How does it compare to ByteDance/Hyper-SD or sd-community/sdxl-flash ?
Updated a month ago2
Possibility for 30fps image generation?
Updated a month ago6
sdv15 train with torchrun successful, but sdxl train with fsdp failed.
Updated a month ago
Current CUDA Device does not support bfloat16. Please switch dtype to float16.
Updated a month ago
Is it possible to integrate with HiDiffusion?
Updated a month ago6
Is it possible to integrate with diffusers?
Updated a month ago1
How to visualize Figure3
Closed a month ago1
Why is uncorrelated noise used in backward_simulation?
Closed a month ago1
Why add the discriminator header on the fake denoiser and not on the real denoiser where the parameters are fixed?
Closed a month ago3
Request for test_folder.py in ImageNet-64x64 Experiments
Closed a month ago2
demo dead 💀
Closed a month ago1
Plans for inpainting model.
Closed a month ago1