You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When I use the training scripts for sdxl and run log_validation. I meet the following error Traceback (most recent call last): File "/maindata/data/shared/public/songtao.tian/test_code/Target-Driven-Distillation/train/SDXL/test_image.py", line 156, in <module> image = pipeline(prompt=prompt, num_inference_steps=steps, guidance_scale=cfg, height=1152, width=864,eta=0.2).images[0] File "/maindata/data/shared/public/songtao.tian/anaconda3/envs/tdd/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) File "/maindata/data/shared/public/songtao.tian/anaconda3/envs/tdd/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py", line 1229, in __call__ latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0] File "/maindata/data/shared/public/songtao.tian/test_code/Target-Driven-Distillation/train/SDXL/scheduler.py", line 232, in step model_output = self.convert_model_output(model_output, sample=sample) File "/maindata/data/shared/public/songtao.tian/test_code/Target-Driven-Distillation/train/SDXL/scheduler.py", line 475, in convert_model_output alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma) File "/maindata/data/shared/public/songtao.tian/anaconda3/envs/tdd/lib/python3.10/site-packages/diffusers/schedulers/scheduling_dpmsolver_singlestep.py", line 464, in _sigma_to_alpha_sigma_t if self.config.use_flow_sigmas: AttributeError: 'FrozenDict' object has no attribute 'use_flow_sigmas'
It seems that the diffusers version is not right?
The text was updated successfully, but these errors were encountered:
When I use the training scripts for sdxl and run log_validation. I meet the following error
Traceback (most recent call last): File "/maindata/data/shared/public/songtao.tian/test_code/Target-Driven-Distillation/train/SDXL/test_image.py", line 156, in <module> image = pipeline(prompt=prompt, num_inference_steps=steps, guidance_scale=cfg, height=1152, width=864,eta=0.2).images[0] File "/maindata/data/shared/public/songtao.tian/anaconda3/envs/tdd/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) File "/maindata/data/shared/public/songtao.tian/anaconda3/envs/tdd/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py", line 1229, in __call__ latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0] File "/maindata/data/shared/public/songtao.tian/test_code/Target-Driven-Distillation/train/SDXL/scheduler.py", line 232, in step model_output = self.convert_model_output(model_output, sample=sample) File "/maindata/data/shared/public/songtao.tian/test_code/Target-Driven-Distillation/train/SDXL/scheduler.py", line 475, in convert_model_output alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma) File "/maindata/data/shared/public/songtao.tian/anaconda3/envs/tdd/lib/python3.10/site-packages/diffusers/schedulers/scheduling_dpmsolver_singlestep.py", line 464, in _sigma_to_alpha_sigma_t if self.config.use_flow_sigmas: AttributeError: 'FrozenDict' object has no attribute 'use_flow_sigmas'
It seems that the diffusers version is not right?
The text was updated successfully, but these errors were encountered: