lalimec/rylmtch 🔢📝 → 🖼️

▶️ 48 runs 📅 Jun 2025 ⚙️ Cog 0.15.5
cartoon lora text-to-image

About

Example Output

Prompt:

"king holding a wooden sign saying "rylmtch" with golden embossed letters, in the background a red dragon lying on the ground eyes closed, surrounded by lava."

Output

Example output

Performance Metrics

10.48s Prediction Time
211.79s Total Time
All Input Parameters
{
  "seed": 123,
  "prompt": "king holding a wooden sign saying \"rylmtch\" with golden embossed letters, in the background a red dragon lying on the ground eyes closed, surrounded by lava.",
  "style_lora_scale": 0.5,
  "character_lora_scale": 0.85
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
prompt (required) Type: string
Prompt for generated image
style_lora_scale Type: numberDefault: 0.5Range: 0 - 1
Scale for style LoRA (0.0 to 1.0)
character_lora_scale Type: numberDefault: 0.85Range: 0 - 1
Scale for character LoRA (0.0 to 1.0)
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 123
Original prompt: king holding a wooden sign saying "rylmtch" with golden embossed letters, in the background a red dragon lying on the ground eyes closed, surrounded by lava.
Full prompt with prefix: 3d model of rylmtch man a cartoon king with a beard and a crown on his head, king holding a wooden sign saying "rylmtch" with golden embossed letters, in the background a red dragon lying on the ground eyes closed, surrounded by lava.
Using static config: 1024x1024, steps=8, guidance=3.0
Loading LoRA models...
Loading character LoRA: cemilal/rylmtch
Using pre-configured HuggingFace token for cemilal/rylmtch
Attempting to download royalmatch-king.safetensors from HuggingFace...
Checking cache and downloading if needed...
Character LoRA not in cache, downloading...
/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/huggingface_hub/file_download.py:943: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
warnings.warn(
Character LoRA download/cache completed in: 1.263s
Character LoRA cached at: /root/.cache/huggingface/hub/models--cemilal--rylmtch/snapshots/41c098d571835b1945c0332871bb8a513ec25c9d/royalmatch-king.safetensors
File exists: True
File size: 153,290,408 bytes (146.2 MB)
Loading character LoRA weights...
Character LoRA loading took: 0.740s
Successfully loaded character LoRA with scale 0.85
Loading style LoRA: cemilal/rylmtch
Using pre-configured HuggingFace token for cemilal/rylmtch
Attempting to download royalmatch-style.safetensors from HuggingFace...
Checking cache and downloading if needed...
Style LoRA not in cache, downloading...
Style LoRA download/cache completed in: 1.761s
Style LoRA cached at: /root/.cache/huggingface/hub/models--cemilal--rylmtch/snapshots/41c098d571835b1945c0332871bb8a513ec25c9d/royalmatch-style.safetensors
File exists: True
File size: 367,788,032 bytes (350.8 MB)
Loading style LoRA weights...
Error during download/cache check: Unable to load weights from checkpoint file for '/root/.cache/huggingface/hub/models--cemilal--rylmtch/snapshots/41c098d571835b1945c0332871bb8a513ec25c9d/royalmatch-style.safetensors' at '/root/.cache/huggingface/hub/models--cemilal--rylmtch/snapshots/41c098d571835b1945c0332871bb8a513ec25c9d/royalmatch-style.safetensors'.
Error loading style LoRA: Unable to load weights from checkpoint file for '/root/.cache/huggingface/hub/models--cemilal--rylmtch/snapshots/41c098d571835b1945c0332871bb8a513ec25c9d/royalmatch-style.safetensors' at '/root/.cache/huggingface/hub/models--cemilal--rylmtch/snapshots/41c098d571835b1945c0332871bb8a513ec25c9d/royalmatch-style.safetensors'.
Exception type: OSError
Full traceback:
Traceback (most recent call last):
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/model_loading_utils.py", line 105, in load_state_dict
return safetensors.torch.load_file(checkpoint_file, device="cpu")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/safetensors/torch.py", line 313, in load_file
with safe_open(filename, framework="pt", device=device) as f:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/model_loading_utils.py", line 116, in load_state_dict
if f.read().startswith("version"):
^^^^^^^^
File "<frozen codecs>", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xfe in position 138064: invalid start byte
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/src/predict.py", line 271, in load_loras
raise download_error
File "/src/predict.py", line 266, in load_loras
self.txt2img_pipe.load_lora_weights(style_lora, adapter_name="style", weight_name="royalmatch-style.safetensors", token=HF_TOKEN)
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/loaders/lora_pipeline.py", line 1658, in load_lora_weights
state_dict, network_alphas = self.lora_state_dict(
^^^^^^^^^^^^^^^^^^^^^
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/loaders/lora_pipeline.py", line 1576, in lora_state_dict
state_dict = cls._fetch_state_dict(
^^^^^^^^^^^^^^^^^^^^^^
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/loaders/lora_base.py", line 307, in _fetch_state_dict
state_dict = load_state_dict(model_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/model_loading_utils.py", line 128, in load_state_dict
raise OSError(
OSError: Unable to load weights from checkpoint file for '/root/.cache/huggingface/hub/models--cemilal--rylmtch/snapshots/41c098d571835b1945c0332871bb8a513ec25c9d/royalmatch-style.safetensors' at '/root/.cache/huggingface/hub/models--cemilal--rylmtch/snapshots/41c098d571835b1945c0332871bb8a513ec25c9d/royalmatch-style.safetensors'.
Set adapters: ['character'] with weights: [0.85]
  0%|          | 0/8 [00:00<?, ?it/s]
 12%|█▎        | 1/8 [00:00<00:04,  1.58it/s]
 25%|██▌       | 2/8 [00:01<00:03,  1.96it/s]
 38%|███▊      | 3/8 [00:01<00:02,  1.90it/s]
 50%|█████     | 4/8 [00:02<00:02,  1.87it/s]
 62%|██████▎   | 5/8 [00:02<00:01,  1.86it/s]
 75%|███████▌  | 6/8 [00:03<00:01,  1.84it/s]
 88%|████████▊ | 7/8 [00:03<00:00,  1.84it/s]
100%|██████████| 8/8 [00:04<00:00,  1.84it/s]
100%|██████████| 8/8 [00:04<00:00,  1.84it/s]
Version Details
Version ID
9dd64ff3ec9d614e3e42e4a93282264c7c105c73aeddab4a575b72f40331f2af
Version Created
June 11, 2025
Run on Replicate →