Text-to-Image
Diffusers
English
lora
flux
pixel-art
game-asset
sprite
character-design
FLUX.2-klein-4B
Instructions to use Limbicnation/pixel-art-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Limbicnation/pixel-art-lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-4B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Limbicnation/pixel-art-lora") prompt = "pixel art sprite, a brave knight in shining armor holding a sword, game asset, transparent background" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Unable to run
#2
by andysg2211 - opened
Thanks for this. I am trying to run this but got error:
Loading weights: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 398/398 [00:00<00:00, 5766.78it/s]
Loading pipeline components...: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 5/5 [00:00<00:00, 5.26it/s]
Traceback (most recent call last):
File "/workspace/test.py", line 9, in <module>
pipe.load_lora_weights("Limbicnation/pixel-art-lora")
File "/opt/conda/lib/python3.10/site-packages/diffusers/loaders/lora_pipeline.py", line 5713, in load_lora_weights
state_dict, metadata = self.lora_state_dict(pretrained_model_name_or_path_or_dict, **kwargs)
File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 88, in _inner_fn
return fn(*args, **kwargs)
File "/opt/conda/lib/python3.10/site-packages/diffusers/loaders/lora_pipeline.py", line 5682, in lora_state_dict
state_dict = _convert_non_diffusers_flux2_lora_to_diffusers(state_dict)
File "/opt/conda/lib/python3.10/site-packages/diffusers/loaders/lora_conversion_utils.py", line 2435, in _convert_non_diffusers_flux2_lora_to_diffusers
raise ValueError(f"`original_state_dict` should be empty at this point but has {original_state_dict.keys()=}.")
ValueError: `original_state_dict` should be empty at this point but has original_state_dict.keys()=dict_keys(['context_embedder.lora_A.weight', 'context_embedder.lora_B.weight', 'double_stream_modulation_img.linear.lora_A.weight', 'double_stream_modulation_img.linear.lora_B.weight', 'double_stream_modulation_txt.linear.lora_A.weight', 'double_stream_modulation_txt.linear.lora_B.weight', 'proj_out.lora_A.weight', 'proj_out.lora_B.weight', 'single_stream_modulation.linear.lora_A.weight', 'single_stream_modulation.linear.lora_B.weight', 'single_transformer_blocks.0.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.0.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.1.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.1.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.10.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.10.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.11.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.11.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.12.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.12.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.13.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.13.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.14.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.14.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.15.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.15.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.16.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.16.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.17.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.17.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.18.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.18.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.19.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.19.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.2.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.2.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.3.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.3.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.4.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.4.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.5.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.5.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.6.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.6.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.7.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.7.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.8.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.8.attn.to_qkv_mlp_proj.lora_B.weight', 'single_transformer_blocks.9.attn.to_qkv_mlp_proj.lora_A.weight', 'single_transformer_blocks.9.attn.to_qkv_mlp_proj.lora_B.weight', 'transformer_blocks.0.attn.add_k_proj.lora_A.weight', 'transformer_blocks.0.attn.add_k_proj.lora_B.weight', 'transformer_blocks.0.attn.add_q_proj.lora_A.weight', 'transformer_blocks.0.attn.add_q_proj.lora_B.weight', 'transformer_blocks.0.attn.add_v_proj.lora_A.weight', 'transformer_blocks.0.attn.add_v_proj.lora_B.weight', 'transformer_blocks.0.attn.to_add_out.lora_A.weight', 'transformer_blocks.0.attn.to_add_out.lora_B.weight', 'transformer_blocks.0.attn.to_k.lora_A.weight', 'transformer_blocks.0.attn.to_k.lora_B.weight', 'transformer_blocks.0.attn.to_out.0.lora_A.weight', 'transformer_blocks.0.attn.to_out.0.lora_B.weight', 'transformer_blocks.0.attn.to_q.lora_A.weight', 'transformer_blocks.0.attn.to_q.lora_B.weight', 'transformer_blocks.0.attn.to_v.lora_A.weight', 'transformer_blocks.0.attn.to_v.lora_B.weight', 'transformer_blocks.0.ff.linear_in.lora_A.weight', 'transformer_blocks.0.ff.linear_in.lora_B.weight', 'transformer_blocks.0.ff.linear_out.lora_A.weight', 'transformer_blocks.0.ff.linear_out.lora_B.weight', 'transformer_blocks.0.ff_context.linear_in.lora_A.weight', 'transformer_blocks.0.ff_context.linear_in.lora_B.weight', 'transformer_blocks.0.ff_context.linear_out.lora_A.weight', 'transformer_blocks.0.ff_context.linear_out.lora_B.weight', 'transformer_blocks.1.attn.add_k_proj.lora_A.weight', 'transformer_blocks.1.attn.add_k_proj.lora_B.weight', 'transformer_blocks.1.attn.add_q_proj.lora_A.weight', 'transformer_blocks.1.attn.add_q_proj.lora_B.weight', 'transformer_blocks.1.attn.add_v_proj.lora_A.weight', 'transformer_blocks.1.attn.add_v_proj.lora_B.weight', 'transformer_blocks.1.attn.to_add_out.lora_A.weight', 'transformer_blocks.1.attn.to_add_out.lora_B.weight', 'transformer_blocks.1.attn.to_k.lora_A.weight', 'transformer_blocks.1.attn.to_k.lora_B.weight', 'transformer_blocks.1.attn.to_out.0.lora_A.weight', 'transformer_blocks.1.attn.to_out.0.lora_B.weight', 'transformer_blocks.1.attn.to_q.lora_A.weight', 'transformer_blocks.1.attn.to_q.lora_B.weight', 'transformer_blocks.1.attn.to_v.lora_A.weight', 'transformer_blocks.1.attn.to_v.lora_B.weight', 'transformer_blocks.1.ff.linear_in.lora_A.weight', 'transformer_blocks.1.ff.linear_in.lora_B.weight', 'transformer_blocks.1.ff.linear_out.lora_A.weight', 'transformer_blocks.1.ff.linear_out.lora_B.weight', 'transformer_blocks.1.ff_context.linear_in.lora_A.weight', 'transformer_blocks.1.ff_context.linear_in.lora_B.weight', 'transformer_blocks.1.ff_context.linear_out.lora_A.weight', 'transformer_blocks.1.ff_context.linear_out.lora_B.weight', 'transformer_blocks.2.attn.add_k_proj.lora_A.weight', 'transformer_blocks.2.attn.add_k_proj.lora_B.weight', 'transformer_blocks.2.attn.add_q_proj.lora_A.weight', 'transformer_blocks.2.attn.add_q_proj.lora_B.weight', 'transformer_blocks.2.attn.add_v_proj.lora_A.weight', 'transformer_blocks.2.attn.add_v_proj.lora_B.weight', 'transformer_blocks.2.attn.to_add_out.lora_A.weight', 'transformer_blocks.2.attn.to_add_out.lora_B.weight', 'transformer_blocks.2.attn.to_k.lora_A.weight', 'transformer_blocks.2.attn.to_k.lora_B.weight', 'transformer_blocks.2.attn.to_out.0.lora_A.weight', 'transformer_blocks.2.attn.to_out.0.lora_B.weight', 'transformer_blocks.2.attn.to_q.lora_A.weight', 'transformer_blocks.2.attn.to_q.lora_B.weight', 'transformer_blocks.2.attn.to_v.lora_A.weight', 'transformer_blocks.2.attn.to_v.lora_B.weight', 'transformer_blocks.2.ff.linear_in.lora_A.weight', 'transformer_blocks.2.ff.linear_in.lora_B.weight', 'transformer_blocks.2.ff.linear_out.lora_A.weight', 'transformer_blocks.2.ff.linear_out.lora_B.weight', 'transformer_blocks.2.ff_context.linear_in.lora_A.weight', 'transformer_blocks.2.ff_context.linear_in.lora_B.weight', 'transformer_blocks.2.ff_context.linear_out.lora_A.weight', 'transformer_blocks.2.ff_context.linear_out.lora_B.weight', 'transformer_blocks.3.attn.add_k_proj.lora_A.weight', 'transformer_blocks.3.attn.add_k_proj.lora_B.weight', 'transformer_blocks.3.attn.add_q_proj.lora_A.weight', 'transformer_blocks.3.attn.add_q_proj.lora_B.weight', 'transformer_blocks.3.attn.add_v_proj.lora_A.weight', 'transformer_blocks.3.attn.add_v_proj.lora_B.weight', 'transformer_blocks.3.attn.to_add_out.lora_A.weight', 'transformer_blocks.3.attn.to_add_out.lora_B.weight', 'transformer_blocks.3.attn.to_k.lora_A.weight', 'transformer_blocks.3.attn.to_k.lora_B.weight', 'transformer_blocks.3.attn.to_out.0.lora_A.weight', 'transformer_blocks.3.attn.to_out.0.lora_B.weight', 'transformer_blocks.3.attn.to_q.lora_A.weight', 'transformer_blocks.3.attn.to_q.lora_B.weight', 'transformer_blocks.3.attn.to_v.lora_A.weight', 'transformer_blocks.3.attn.to_v.lora_B.weight', 'transformer_blocks.3.ff.linear_in.lora_A.weight', 'transformer_blocks.3.ff.linear_in.lora_B.weight', 'transformer_blocks.3.ff.linear_out.lora_A.weight', 'transformer_blocks.3.ff.linear_out.lora_B.weight', 'transformer_blocks.3.ff_context.linear_in.lora_A.weight', 'transformer_blocks.3.ff_context.linear_in.lora_B.weight', 'transformer_blocks.3.ff_context.linear_out.lora_A.weight', 'transformer_blocks.3.ff_context.linear_out.lora_B.weight', 'transformer_blocks.4.attn.add_k_proj.lora_A.weight', 'transformer_blocks.4.attn.add_k_proj.lora_B.weight', 'transformer_blocks.4.attn.add_q_proj.lora_A.weight', 'transformer_blocks.4.attn.add_q_proj.lora_B.weight', 'transformer_blocks.4.attn.add_v_proj.lora_A.weight', 'transformer_blocks.4.attn.add_v_proj.lora_B.weight', 'transformer_blocks.4.attn.to_add_out.lora_A.weight', 'transformer_blocks.4.attn.to_add_out.lora_B.weight', 'transformer_blocks.4.attn.to_k.lora_A.weight', 'transformer_blocks.4.attn.to_k.lora_B.weight', 'transformer_blocks.4.attn.to_out.0.lora_A.weight', 'transformer_blocks.4.attn.to_out.0.lora_B.weight', 'transformer_blocks.4.attn.to_q.lora_A.weight', 'transformer_blocks.4.attn.to_q.lora_B.weight', 'transformer_blocks.4.attn.to_v.lora_A.weight', 'transformer_blocks.4.attn.to_v.lora_B.weight', 'transformer_blocks.4.ff.linear_in.lora_A.weight', 'transformer_blocks.4.ff.linear_in.lora_B.weight', 'transformer_blocks.4.ff.linear_out.lora_A.weight', 'transformer_blocks.4.ff.linear_out.lora_B.weight', 'transformer_blocks.4.ff_context.linear_in.lora_A.weight', 'transformer_blocks.4.ff_context.linear_in.lora_B.weight', 'transformer_blocks.4.ff_context.linear_out.lora_A.weight', 'transformer_blocks.4.ff_context.linear_out.lora_B.weight', 'x_embedder.lora_A.weight', 'x_embedder.lora_B.weight']).
root@flux-diffusers-557588d7c5-qf5ms:/workspace#
What versions are you using?