Text-to-Image
Diffusers
Safetensors
GGUF
English
image-generation
diffusion
anime
z-image
z-anime
comfyui
fp8
bf16
aio
Instructions to use SeeSee21/Z-Anime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SeeSee21/Z-Anime with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SeeSee21/Z-Anime", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Errors when running the example script
#13
by xmxhuihui - opened
Hi,
I have encountered entry not found error when running your script. I assume that it is because there is no model_index.json file in the base folder. Can you manage to fix it?
Traceback (most recent call last):
File "/root/autodl-tmp/test.py", line 4, in <module>
pipe = ZImagePipeline.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 88, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/diffusers/pipelines/pipeline_utils.py", line 853, in from_pretrained
cached_folder = cls.download(
^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 88, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/diffusers/pipelines/pipeline_utils.py", line 1636, in download
config_file = hf_hub_download(
^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 88, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 997, in hf_hub_download
return _hf_hub_download_to_cache_dir(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1072, in _hf_hub_download_to_cache_dir
(url_to_download, etag, commit_hash, expected_size, xet_file_data, head_call_error) = _get_metadata_or_catch_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1669, in _get_metadata_or_catch_error
metadata = get_hf_file_metadata(
^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 88, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1591, in get_hf_file_metadata
response = _httpx_follow_relative_redirects_with_backoff(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 692, in _httpx_follow_relative_redirects_with_backoff
hf_raise_for_status(response)
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 781, in hf_raise_for_status
raise _format(RemoteEntryNotFoundError, message, response, repo_type=repo_type, repo_id=repo_id) from e
huggingface_hub.errors.RemoteEntryNotFoundError: 404 Client Error. (Request ID: Root=1-6a0ba1aa-7b22a4492983ae4a2a23622c;5e7a3c9a-d46f-4cde-a5b8-9653e34f7f14)
Entry Not Found for url: https://hf-mirror.com/SeeSee21/Z-Anime/resolve/main/model_index.json.
Also even if I run locally with ZImagePipeline, the text encoder seem not match the loaded checkpoint file, which lead to a failed generation that the generated image content mismatches the prompt.
[transformers] Qwen3ForCausalLM LOAD REPORT from: /root/.cache/huggingface/hub/models--SeeSee21--Z-Anime/snapshots/0f5fb51464638a2f7328a1d74590281e63e1fde2/diffusers/text_encoder
Key | Status | |
---------------------------------------------+------------+--+-
model.layers.{0...35}.mlp.gate_proj.scale | UNEXPECTED | |
model.layers.{0...35}.mlp.down_proj.scale | UNEXPECTED | |
model.layers.{0...35}.mlp.up_proj.scale | UNEXPECTED | |
model.layers.{0...35}.self_attn.q_proj.scale | UNEXPECTED | |
model.layers.{0...35}.self_attn.v_proj.scale | UNEXPECTED | |
model.layers.{0...35}.self_attn.o_proj.scale | UNEXPECTED | |
model.layers.{0...35}.self_attn.k_proj.scale | UNEXPECTED | |
lm_head.scale | UNEXPECTED | |
Notes:
- UNEXPECTED: can be ignored when loading from different task/architecture; not ok if you expect identical arch.