INFO @@@@@ Starting Diffuzes API @@@@@
INFO Text2Image Model: Lykon/DreamShaper
INFO Text2Image Pipeline: Vanilla
INFO Inpainting Model: None
INFO Device: cuda
INFO Output Path: None
INFO Token Identifier:
INFO Token Embeddings URL:
INFO Loading x2img model…
safety_checker/model.safetensors not found
The config attributes {‘addition_embed_type’: None, ‘addition_embed_type_num_heads’: 64, ‘encoder_hid_dim_type’: None, ‘time_embedding_dim’: None} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
ERROR: Traceback (most recent call last):
File “/genAI/venv/lib/python3.10/site-packages/starlette/routing.py”, line 671, in lifespan
async with self.lifespan_context(app):
File “/genAI/venv/lib/python3.10/site-packages/starlette/routing.py”, line 566, in aenter
await self._router.startup()
File “/genAI/venv/lib/python3.10/site-packages/starlette/routing.py”, line 648, in startup
await handler()
File “/genAI/venv/lib/python3.10/site-packages/diffuzers/api/main.py”, line 46, in startup_event
app.state.x2img_model = X2Image(
File “”, line 9, in init
File “/genAI/venv/lib/python3.10/site-packages/diffuzers/x2image.py”, line 72, in post_init
self.text2img_pipeline = DiffusionPipeline.from_pretrained(
File “/genAI/venv/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.py”, line 1009, in from_pretrained
loaded_sub_model = load_sub_model(
File “/genAI/venv/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.py”, line 444, in load_sub_model
loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
File “/genAI/venv/lib/python3.10/site-packages/diffusers/models/modeling_utils.py”, line 561, in from_pretrained
raise ValueError(
ValueError: Cannot load <class ‘diffusers.models.autoencoder_kl.AutoencoderKL’> from /root/.cache/huggingface/hub/models–Lykon–DreamShaper/snapshots/da192fb823b14d306f52f9418b25923479e666ea/vae because the following keys are missing:
decoder.mid_block.attentions.0.query.weight, decoder.mid_block.attentions.0.value.bias, decoder.mid_block.attentions.0.key.bias, encoder.mid_block.attentions.0.query.bias, decoder.mid_block.attentions.0.proj_attn.bias, encoder.mid_block.attentions.0.value.weight, encoder.mid_block.attentions.0.query.weight, decoder.mid_block.attentions.0.query.bias, encoder.mid_block.attentions.0.proj_attn.weight, decoder.mid_block.attentions.0.proj_attn.weight, encoder.mid_block.attentions.0.key.bias, encoder.mid_block.attentions.0.key.weight, decoder.mid_block.attentions.0.value.weight, encoder.mid_block.attentions.0.proj_attn.bias, decoder.mid_block.attentions.0.key.weight, encoder.mid_block.attentions.0.value.bias.
Please make sure to pass low_cpu_mem_usage=False and device_map=None if you want to randomly initialize those weights or else make sure your checkpoint file is correct.
Did you fix it? I have the same problem. Would love to know.
No, I used automatic1111.