Luo-Yihong

/

yoso_pixart1024

like 12

Hi there,

Was trying to run the script in model card, and getting following, what did I do wrong? Thanks!

D:\ComfyUI\venv\lib\site-packages\transformers\utils\hub.py:124: FutureWarning: Using TRANSFORMERS_CACHE is deprecated and will be removed in v5 of Transformers. Use HF_HOME instead.
warnings.warn(
D:\ComfyUI\venv\lib\site-packages\diffusers\models\transformers\transformer_2d.py:34: FutureWarning: Transformer2DModelOutput is deprecated and will be removed in version 1.0.0. Importing Transformer2DModelOutput from diffusers.models.transformer_2d is deprecated and this will be removed in a future version. Please use from diffusers.models.modeling_outputs import Transformer2DModelOutput, instead.
deprecate("Transformer2DModelOutput", "1.0.0", deprecation_message)
config.json: 100%
 769/769 [00:00<00:00, 24.5kB/s]
diffusion_pytorch_model.safetensors: 100%
 2.45G/2.45G [01:14<00:00, 31.5MB/s]
model_index.json: 100%
 452/452 [00:00<?, ?B/s]
Fetching 15 files: 100%
 15/15 [09:39<00:00, 93.78s/it]
text_encoder/config.json: 100%
 907/907 [00:00<00:00, 29.1kB/s]
scheduler/scheduler_config.json: 100%
 655/655 [00:00<00:00, 21.0kB/s]
(…)ext_encoder/model.safetensors.index.json: 100%
 19.9k/19.9k [00:00<00:00, 1.28MB/s]
tokenizer/added_tokens.json: 100%
 2.59k/2.59k [00:00<00:00, 1.15MB/s]
model-00001-of-00004.safetensors: 100%
 4.99G/4.99G [09:21<00:00, 21.1MB/s]
model-00004-of-00004.safetensors: 100%
 4.19G/4.19G [05:26<00:00, 32.7MB/s]
model-00003-of-00004.safetensors: 100%
 4.87G/4.87G [09:38<00:00, 35.9MB/s]
model-00002-of-00004.safetensors: 100%
 5.00G/5.00G [06:40<00:00, 29.4MB/s]
tokenizer/tokenizer_config.json: 100%
 20.5k/20.5k [00:00<00:00, 931kB/s]
transformer/config.json: 100%
 718/718 [00:00<00:00, 60.9kB/s]
tokenizer/special_tokens_map.json: 100%
 2.54k/2.54k [00:00<00:00, 151kB/s]
spiece.model: 100%
 792k/792k [00:00<00:00, 2.66MB/s]
vae/config.json: 100%
 759/759 [00:00<00:00, 152kB/s]
diffusion_pytorch_model.safetensors: 100%
 335M/335M [00:12<00:00, 29.6MB/s]
Loading pipeline components...: 100%
 5/5 [00:17<00:00,  5.28s/it]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading checkpoint shards: 100%
 4/4 [00:16<00:00,  4.36s/it]
  0%
 0/1 [00:13<?, ?it/s]
D:\ComfyUI\venv\lib\site-packages\diffusers\models\attention_processor.py:1584: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.)
hidden_states = F.scaled_dot_product_attention(

AttributeError Traceback (most recent call last)
Cell In[1], line 15
13 pipe.scheduler.config.prediction_type = "v_prediction"
14 generator = torch.manual_seed(318)
---> 15 imgs = pipe(prompt="Pirate ship trapped in a cosmic maelstrom nebula, rendered in cosmic beach whirlpool engine, volumetric lighting, spectacular, ambient lights, light pollution, cinematic atmosphere, art nouveau style, illustration art artwork by SenseiJaye, intricate detail.",
16 num_inference_steps=1,
17 num_images_per_prompt = 1,
18 generator = generator,
19 guidance_scale=1.,
20 )[0]
21 imgs[0]

File D:\ComfyUI\venv\lib\site-packages\torch\utils_contextlib.py:115, in context_decorator..decorate_context(*args, **kwargs)
112 @functools.wraps(func)
113 def decorate_context(*args, **kwargs):
114 with ctx_factory():
--> 115 return func(*args, **kwargs)

File D:\ComfyUI\venv\lib\site-packages\diffusers\pipelines\pixart_alpha\pipeline_pixart_alpha.py:942, in PixArtAlphaPipeline.call(self, prompt, negative_prompt, num_inference_steps, timesteps, sigmas, guidance_scale, num_images_per_prompt, height, width, eta, generator, latents, prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask, output_type, return_dict, callback, callback_steps, clean_caption, use_resolution_binning, max_sequence_length, **kwargs)
939 # compute previous image: x_t -> x_t-1
940 if num_inference_steps == 1:
941 # For DMD one step sampling: https://arxiv.org/abs/2311.18828
--> 942 latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).pred_original_sample
943 else:
944 latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]

AttributeError: 'LCMSchedulerOutput' object has no attribute 'pred_original_sample'