Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,7 @@ samples/1764461752018__000001500_1.jpg filter=lfs diff=lfs merge=lfs -text
 samples/1764463152130__000002250_1.jpg filter=lfs diff=lfs merge=lfs -text
 samples/1764463619358__000002500_1.jpg filter=lfs diff=lfs merge=lfs -text
 samples/1764464065957__000002750_1.jpg filter=lfs diff=lfs merge=lfs -text
+xgb/samples/1764461752018__000001500_1.jpg filter=lfs diff=lfs merge=lfs -text
+xgb/samples/1764463152130__000002250_1.jpg filter=lfs diff=lfs merge=lfs -text
+xgb/samples/1764463619358__000002500_1.jpg filter=lfs diff=lfs merge=lfs -text
+xgb/samples/1764464065957__000002750_1.jpg filter=lfs diff=lfs merge=lfs -text

xgb/.job_config.json

@@ -0,0 +1,133 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "xgb",
+    "process": [
+      {
+        "type": "diffusion_trainer",
+        "training_folder": "/workspace/ai-toolkit/output",
+        "sqlite_db_path": "/workspace/ai-toolkit/aitk_db.db",
+        "device": "cuda",
+        "trigger_word": "xgb",
+        "performance_log_every": 10,
+        "network": {
+          "type": "lora",
+          "linear": 32,
+          "linear_alpha": 32,
+          "conv": 16,
+          "conv_alpha": 16,
+          "lokr_full_rank": true,
+          "lokr_factor": -1,
+          "network_kwargs": {
+            "ignore_if_contains": []
+          }
+        },
+        "save": {
+          "dtype": "bf16",
+          "save_every": 250,
+          "max_step_saves_to_keep": 4,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/workspace/ai-toolkit/datasets/xgb",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "xgb",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "cache_latents_to_disk": false,
+            "is_reg": false,
+            "network_weight": 1,
+            "resolution": [
+              512,
+              768,
+              1024
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 1,
+            "do_i2v": true,
+            "flip_x": false,
+            "flip_y": false
+          }
+        ],
+        "train": {
+          "batch_size": 1,
+          "bypass_guidance_embedding": false,
+          "steps": 3000,
+          "gradient_accumulation": 1,
+          "train_unet": true,
+          "train_text_encoder": false,
+          "gradient_checkpointing": true,
+          "noise_scheduler": "flowmatch",
+          "optimizer": "adamw8bit",
+          "timestep_type": "weighted",
+          "content_or_style": "balanced",
+          "optimizer_params": {
+            "weight_decay": 0.0001
+          },
+          "unload_text_encoder": false,
+          "cache_text_embeddings": false,
+          "lr": 0.0001,
+          "ema_config": {
+            "use_ema": false,
+            "ema_decay": 0.99
+          },
+          "skip_first_sample": false,
+          "force_first_sample": false,
+          "disable_sampling": false,
+          "dtype": "bf16",
+          "diff_output_preservation": false,
+          "diff_output_preservation_multiplier": 1,
+          "diff_output_preservation_class": "person",
+          "switch_boundary_every": 1,
+          "loss_type": "mse"
+        },
+        "model": {
+          "name_or_path": "/workspace/Z-Image-Turbo",
+          "quantize": true,
+          "qtype": "qfloat8",
+          "quantize_te": true,
+          "qtype_te": "qfloat8",
+          "arch": "zimage:turbo",
+          "low_vram": false,
+          "model_kwargs": {},
+          "layer_offloading": false,
+          "layer_offloading_text_encoder_percent": 1,
+          "layer_offloading_transformer_percent": 1,
+          "assistant_lora_path": "/workspace/Z-Image-Turbo/zimage_turbo_training_adapter_v1.safetensors"
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "width": 1024,
+          "height": 1024,
+          "samples": [
+            {
+              "prompt": "一个黑色短发的女孩对着镜头眨眼（Wink），头顶推着一副墨镜。她穿着黑色的长袖上衣或外套，一只手托着下巴。脖子上戴着一条精致的圆环项链，表情俏皮可爱，白色背景。 xgb"
+            },
+            {
+              "prompt": "一个紫色波波头（Bob）短发的女孩，做出俏皮的姿势，双手握拳像猫爪一样。她穿着浅蓝色的针织两件套（背心和开衫）搭配牛仔短裤，看起来充满活力，白色背景。 xgb"
+            },
+            {
+              "prompt": "一个银白色短发的女子，气质像洋娃娃般精致。她穿着白色的蕾丝露肩连衣裙，脖子上戴着白色的蕾丝项圈（Choker）。她身体微微前倾，眼神清澈，风格梦幻优雅，白色背景。 xgb"
+            }
+          ],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 1,
+          "sample_steps": 8,
+          "num_frames": 1,
+          "fps": 1
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

xgb/config.yaml

@@ -0,0 +1,125 @@
+job: extension
+config:
+  name: xgb
+  process:
+  - type: diffusion_trainer
+    training_folder: /workspace/ai-toolkit/output
+    sqlite_db_path: /workspace/ai-toolkit/aitk_db.db
+    device: cuda
+    trigger_word: xgb
+    performance_log_every: 10
+    network:
+      type: lora
+      linear: 32
+      linear_alpha: 32
+      conv: 16
+      conv_alpha: 16
+      lokr_full_rank: true
+      lokr_factor: -1
+      network_kwargs:
+        ignore_if_contains: []
+    save:
+      dtype: bf16
+      save_every: 250
+      max_step_saves_to_keep: 4
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /workspace/ai-toolkit/datasets/xgb
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: xgb
+      caption_ext: txt
+      caption_dropout_rate: 0.05
+      cache_latents_to_disk: false
+      is_reg: false
+      network_weight: 1
+      resolution:
+      - 512
+      - 768
+      - 1024
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 1
+      do_i2v: true
+      flip_x: false
+      flip_y: false
+    train:
+      batch_size: 1
+      bypass_guidance_embedding: false
+      steps: 3000
+      gradient_accumulation: 1
+      train_unet: true
+      train_text_encoder: false
+      gradient_checkpointing: true
+      noise_scheduler: flowmatch
+      optimizer: adamw8bit
+      timestep_type: weighted
+      content_or_style: balanced
+      optimizer_params:
+        weight_decay: 0.0001
+      unload_text_encoder: false
+      cache_text_embeddings: false
+      lr: 0.0001
+      ema_config:
+        use_ema: false
+        ema_decay: 0.99
+      skip_first_sample: false
+      force_first_sample: false
+      disable_sampling: false
+      dtype: bf16
+      diff_output_preservation: false
+      diff_output_preservation_multiplier: 1
+      diff_output_preservation_class: person
+      switch_boundary_every: 1
+      loss_type: mse
+    model:
+      name_or_path: /workspace/Z-Image-Turbo
+      quantize: true
+      qtype: qfloat8
+      quantize_te: true
+      qtype_te: qfloat8
+      arch: zimage:turbo
+      low_vram: false
+      model_kwargs: {}
+      layer_offloading: false
+      layer_offloading_text_encoder_percent: 1
+      layer_offloading_transformer_percent: 1
+      assistant_lora_path: /workspace/Z-Image-Turbo/zimage_turbo_training_adapter_v1.safetensors
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 1024
+      height: 1024
+      samples:
+      - prompt: "\u4E00\u4E2A\u9ED1\u8272\u77ED\u53D1\u7684\u5973\u5B69\u5BF9\u7740\
+          \u955C\u5934\u7728\u773C\uFF08Wink\uFF09\uFF0C\u5934\u9876\u63A8\u7740\u4E00\
+          \u526F\u58A8\u955C\u3002\u5979\u7A7F\u7740\u9ED1\u8272\u7684\u957F\u8896\
+          \u4E0A\u8863\u6216\u5916\u5957\uFF0C\u4E00\u53EA\u624B\u6258\u7740\u4E0B\
+          \u5DF4\u3002\u8116\u5B50\u4E0A\u6234\u7740\u4E00\u6761\u7CBE\u81F4\u7684\
+          \u5706\u73AF\u9879\u94FE\uFF0C\u8868\u60C5\u4FCF\u76AE\u53EF\u7231\uFF0C\
+          \u767D\u8272\u80CC\u666F\u3002 xgb"
+      - prompt: "\u4E00\u4E2A\u7D2B\u8272\u6CE2\u6CE2\u5934\uFF08Bob\uFF09\u77ED\u53D1\
+          \u7684\u5973\u5B69\uFF0C\u505A\u51FA\u4FCF\u76AE\u7684\u59FF\u52BF\uFF0C\
+          \u53CC\u624B\u63E1\u62F3\u50CF\u732B\u722A\u4E00\u6837\u3002\u5979\u7A7F\
+          \u7740\u6D45\u84DD\u8272\u7684\u9488\u7EC7\u4E24\u4EF6\u5957\uFF08\u80CC\
+          \u5FC3\u548C\u5F00\u886B\uFF09\u642D\u914D\u725B\u4ED4\u77ED\u88E4\uFF0C\
+          \u770B\u8D77\u6765\u5145\u6EE1\u6D3B\u529B\uFF0C\u767D\u8272\u80CC\u666F\
+          \u3002 xgb"
+      - prompt: "\u4E00\u4E2A\u94F6\u767D\u8272\u77ED\u53D1\u7684\u5973\u5B50\uFF0C\
+          \u6C14\u8D28\u50CF\u6D0B\u5A03\u5A03\u822C\u7CBE\u81F4\u3002\u5979\u7A7F\
+          \u7740\u767D\u8272\u7684\u857E\u4E1D\u9732\u80A9\u8FDE\u8863\u88D9\uFF0C\
+          \u8116\u5B50\u4E0A\u6234\u7740\u767D\u8272\u7684\u857E\u4E1D\u9879\u5708\
+          \uFF08Choker\uFF09\u3002\u5979\u8EAB\u4F53\u5FAE\u5FAE\u524D\u503E\uFF0C\
+          \u773C\u795E\u6E05\u6F88\uFF0C\u98CE\u683C\u68A6\u5E7B\u4F18\u96C5\uFF0C\
+          \u767D\u8272\u80CC\u666F\u3002 xgb"
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 1
+      sample_steps: 8
+      num_frames: 1
+      fps: 1
+meta:
+  name: xgb
+  version: '1.0'

xgb/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e82fae7305259320db1f5686007ea58358a86f685abe852cc02690bf941bb81
+size 173288293

xgb/pid.txt

@@ -0,0 +1 @@
+62656

xgb/xgb_000002000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eee9c0b887eb1968531da39d568812fee88ac7b0e2d28895f3a38acffcf8875
+size 170128248

xgb/xgb_000002250.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c82ba1a77587ed31919f63f1ed55dbd57d8e46045bb43a485d4cad1ea87382
+size 170128248

xgb/xgb_000002500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfebb6aac0de4264e03ee3eec789f2a8dd50994b41e225f0a297feb7840973fc
+size 170128248

xgb/xgb_000002750.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe82b6afdbf417a761e41fe9ce9ae78b020fae787004b9038d1f360f5ecd474
+size 170128248