Stylloha

文本編碼器未進行訓練。你可以重用基礎模型的文本編碼器進行推理。

訓練設置

• 訓練輪數：3
• 訓練步數：6000
• 學習率：0.0001
  • 學習率調度：多項式
  • 熱身步數：100
• 最大梯度值：2.0
• 有效批量大小：3
  • 微批量大小：3
  • 梯度累積步數：1
  • GPU數量：1
• 梯度檢查點：True
• 預測類型：flow_matching (額外參數=['shift=3', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0'])
• 優化器：adamw_bf16
• 可訓練參數精度：Pure BF16
• 基礎模型精度：no_change
• 字幕丟棄概率：0.05%

LyCORIS配置

{
    "algo": "loha",
    "multiplier": 1.0,
    "linear_dim": 32,
    "linear_alpha": 16,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

數據集

💻 使用示例

基礎用法

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights


def download_adapter(repo_id: str):
    import os
    from huggingface_hub import hf_hub_download
    adapter_filename = "pytorch_lora_weights.safetensors"
    cache_dir = os.environ.get('HF_PATH', os.path.expanduser('~/.cache/huggingface/hub/models'))
    cleaned_adapter_path = repo_id.replace("/", "_").replace("\\", "_").replace(":", "_")
    path_to_adapter = os.path.join(cache_dir, cleaned_adapter_path)
    path_to_adapter_file = os.path.join(path_to_adapter, adapter_filename)
    os.makedirs(path_to_adapter, exist_ok=True)
    hf_hub_download(
        repo_id=repo_id, filename=adapter_filename, local_dir=path_to_adapter
    )

    return path_to_adapter_file
    
model_id = 'black-forest-labs/FLUX.1-dev'
adapter_repo_id = 'quzo/stylloha'
adapter_filename = 'pytorch_lora_weights.safetensors'
adapter_file_path = download_adapter(repo_id=adapter_repo_id)
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer)
wrapper.merge_to()

prompt = "A photo-realistic image of a cat"


## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it during inference time.
#from optimum.quanto import quantize, freeze, qint8
#quantize(pipeline.transformer, weights=qint8)
#freeze(pipeline.transformer)
    
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
model_output = pipeline(
    prompt=prompt,
    num_inference_steps=20,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]

model_output.save("output.png", format="PNG")

高級用法

# 高級用法可根據具體需求對推理過程進行更多定製，例如調整參數、使用不同的採樣器等。
# 這裡可以根據實際情況添加更多的代碼示例和說明。

📄 許可證

許可證類型：other