Skip to content

Nondescript error popup when trying to train Stable Diffusion XL #523

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Crazygird opened this issue Jun 29, 2024 · 1 comment
Open

Nondescript error popup when trying to train Stable Diffusion XL #523

Crazygird opened this issue Jun 29, 2024 · 1 comment

Comments

@Crazygird
Copy link

Screenshot 2024-06-29 at 1 13 15 PM

Resolution: 768x768
Iterations: 2000
Size: 16

Mac M2, 16G of RAM

@JV-conseil
Copy link

JV-conseil commented Apr 4, 2025

Empty AssertionError when reviewing logs with Show Logs 👇

got b2py rapp lora_training {
    "dataset_path": "~/dataset",
    "selected_sd_model": "Stable Diffusion XL Base 1.0",
    "img_width": 1216,
    "img_height": 1216,
    "out_dir": "~/train_model/",
    "out_name": "T1 SD XL Base 1.0",
    "train_iters": 1500,
    "lora_rank": 8,
    "applet_name": "applet_lora_training",
    "model_tdict_path": "~/.diffusionbee/downloaded_assets/Stable Diffusion XL Base 1.0_sd_xl_base_1.0_f8.tdict",
    "available_text_emb_words": {},
    "num_steps": 25,
}

[SD] dataset : [
    (
        "~/dataset/1.jpg",
        "The image shows a person with short brown hair smiling at the camera. The individual is wearing a dark-colored top or sweater that appears to be made of a knit fabric. The background is plain and light-colored, providing no distractions from the subject. There are no discernible objects or text in the image.",
    ),
    (
        "~/dataset/2.jpg",
        "The image features a person with short brown hair, wearing a dark green top with lace detailing at the neckline. The individual is smiling directly at the camera, and their expression appears friendly and approachable. The background is plain and light-colored, providing no distractions from the subject. There are no discernible texts or additional objects in the image.",
    ),
    (
        "~/dataset/3.jpg",
        "The image shows a person with short brown hair smiling at the camera. The individual is wearing a dark green top with lace detailing around the neckline and shoulders. The background is plain and light-colored, providing no distractions from the subject.",
    ),
    ...
]

json pos 384 450131

Traceback (most recent call last):
File "diffusionbee_backend.py", line 225, in diffusion_bee_main
File "applets/applets.py", line 16, in run_applet
File "applets/lora_training.py", line 290, in run
File "stable_diffusion/utils/model_interface.py", line 65, in create_sd_model_with_weights
File "stable_diffusion/utils/model_interface.py", line 29, in load_weights_model
File "build/int_1.py", line 1020, in int_1.ModelInterface.load_from_tdict
File "build/int_1.py", line 162, in int_1.load_from_tdict
AssertionError

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants