触发词
文件清单 线路:原始(huggingface.co) · 切换
下载后放进对应的 ComfyUI 目录。models/ 指 ComfyUI 的模型根目录。
说明
1111 - MOSS Image Asian Utopian
作者:hinablue
Introduction - R4 使用全新 7,660 筆資料集,包過日本、台灣、韓國與泰國臉孔重新訓練。 Retrained on a brand-new dataset of 7,660 samples featuring Japanese, Taiwanese, Korean, and Thai faces. 日本、台湾、韓国、タイの顔データを含む、新規の7,660件のデータセットを使用して再学習を行いました。 일본, 대만, 한국, 태국인의 얼굴이 포함된 새로운 7,660건의 데이터셋을 사용하여 재학습을 진행했습니다. More Information https://huggingface.co/hinablue/1111-MOSSImage-Asian-Utopian Introduction - UBW 使用篩選過的 8,000 筆資料集,在 Base 模型下訓練 Full fine-tuning Lora,針對肢體、動作、表情等不同方向準備資料集來調整訓練成果。最後使用分層權重,融合回原有模型。 原本想融合 8-steps Lora,但最終想保留更多可操作性所以沒有這樣做。所以,可以自由搭配 8-steps 或 4-steps 的加速 Lora 來使用。 Trained a full fine-tuning LoRA on the Base model using a curated dataset of 8,000 samples, with data specifically structured across different aspects—such as anatomy, poses, and facial expressions—to fine-tune the results. Finally, layer-wise weight merging was applied to fuse it back into the original base model. I initially considered merging an 8-step LoRA directly, but ultimately decided against it to preserve greater flexibility and control. Therefore, you are free to pair this model with your preferred 8-step or 4-step acceleration LoRAs. 厳選した8,000件のデータセットを使用し、Baseモデル上でFull fine-tuning LoRAの学習を行いました。手足・四肢、ポーズ・動作、表情など多角的な観点からデータを準備し、出力結果を調整しています。最終的に、層別重み付け(Layer-wise)を用いて元のベースモデルへマージしました。 当初は8-steps LoRAのマージも検討しましたが、プロンプト追従性や汎用性(操作の自由度)をより高く維持するため、今回は見送りました。そのため、お好みの8-stepsまたは4-stepsの高速化LoRAと自由に組み合わせてご使用いただけます。 엄선된 8,000건의 데이터셋을 활용하여 Base 모델 기반으로 Full fine-tuning LoRA 학습을 진행했습니다. 사지 및 신체 표현, 포즈와 동작, 표정 등 다양한 방면으로 데이터셋을 세분화하여 준비함으로써 학습 완성도를 조율했습니다. 최종적으로는 레이어별 가중치 병합(Layer-wise merge)을 적용하여 기존 베이스 모델에 융합했습니다. 원래는 8-steps LoRA를 직접 병합하는 방안도 고려했으나, 사용자의 조작 유연성과 자유도를 최대한 보존하기 위해 적용하지 않았습니다. 따라서 취향에 맞춰 8-steps 또는 4-steps 고속화 가속 LoRA와 자유롭게 조합하여 사용하실 수 있습니다. Recommend Resolution: 1.2 - 1.6 Megapixels DMD Loras: https://huggingface.co/lodestones/MOSS-Image-Base-8-steps-dmd https://huggingface.co/lodestones/MOSS-Image-SFT-8-steps-dmd Merge MOSS Image SPF + Base, the layer-wise weights used are as follows: video_embedder=0.30 text_embedder.proj=0.30 text_embedder.blocks=0.24 time_embedding=0.36 shared_block_modulation=0.30 layers: layers.0=0.25 layers.1=0.25 layers.2=0.25 layers.3=0.25 layers.4=0.25 layers.5=0.25 layers.6=0.25 layers.7=0.25 layers.8=0.32 layers.9=0.32 layers.10=0.32 layers.11=0.32 layers.12=0.32 layers.13=0.32 layers.14=0.52 layers.15=0.52 layers.16=0.52 layers.17=0.52 layers.18=0.52 layers.19=0.52 layers.20=0.52 layers.21=0.52 layers.22=0.64 layers.23=0.64 layers.24=0.64 layers.25=0.64 layers.26=0.64 layers.27=0.64 layers.28=0.64 layers.29=0.64 layers.30=0.64 layers.31=0.64 layers.32=0.64 layers.33=0.64 layers.34=0.64 layers.35=0.64 layers.36=0.72 layers.37=0.72 layers.38=0.72 layers.39=0.72 layers.40=0.72 layers.41=0.72 final_norm_video.weight=0.30 final_linear_video.weight=0.50 video_head_modulation=0.30Full Lora fine-tuning was incorporated, with a batch size of 2, training for 4 epochs on a dataset of 7,780 datasets. The fusion weights were set to 0.7. Lora Trainer: https://github.com/KohakuBlueleaf/KohakuMossTrainer License Apache-2.0. This is a derivative of Apache-2.0 upstream weights. Keep the upstream notices and state your changes when redistributing.
