Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+samples/1758216469902__000000000_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758216565461__000000000_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758216661314__000000000_2.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758216743963__000000000_3.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758216839275__000000000_4.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758216935285__000000000_5.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758217030615__000000000_6.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758222307301__000000250_3.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758222405233__000000250_4.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758222502194__000000250_5.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758222600487__000000250_6.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758223932533__000000300_3.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758224030235__000000300_4.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758224126955__000000300_5.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758224224338__000000300_6.jpg filter=lfs diff=lfs merge=lfs -text

.job_config.json

@@ -0,0 +1,161 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "The_Cosmic_Drift_Slider",
+    "process": [
+      {
+        "type": "concept_slider",
+        "training_folder": "/app/ai-toolkit/output",
+        "sqlite_db_path": "/app/ai-toolkit/aitk_db.db",
+        "device": "cuda",
+        "trigger_word": null,
+        "performance_log_every": 10,
+        "network": {
+          "type": "lora",
+          "linear": 4,
+          "linear_alpha": 4,
+          "conv": 16,
+          "conv_alpha": 16,
+          "lokr_full_rank": true,
+          "lokr_factor": -1,
+          "network_kwargs": {
+            "ignore_if_contains": []
+          }
+        },
+        "save": {
+          "dtype": "bf16",
+          "save_every": 25,
+          "max_step_saves_to_keep": 4,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/app/ai-toolkit/datasets/the_cosmic_drift_slider",
+            "control_path": null,
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "cache_latents_to_disk": false,
+            "is_reg": false,
+            "network_weight": 1,
+            "resolution": [
+              512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 1,
+            "do_i2v": true,
+            "flip_x": true,
+            "flip_y": false
+          }
+        ],
+        "train": {
+          "batch_size": 4,
+          "bypass_guidance_embedding": false,
+          "steps": 300,
+          "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": true,
+          "cache_text_embeddings": false,
+          "lr": 0.001,
+          "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
+        },
+        "model": {
+          "name_or_path": "Qwen/Qwen-Image",
+          "quantize": true,
+          "qtype": "uint3|ostris/accuracy_recovery_adapters/qwen_image_torchao_uint3.safetensors",
+          "quantize_te": true,
+          "qtype_te": "qfloat8",
+          "arch": "qwen_image",
+          "low_vram": true,
+          "model_kwargs": {}
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "width": 1024,
+          "height": 1024,
+          "samples": [
+            {
+              "prompt": "A medium, eye-level shot of a small group of friends sitting on the grass in a park, chatting on a sunny afternoon. They are wearing simple t-shirts and jeans.",
+              "network_multiplier": "-2.0",
+              "seed": 42
+            },
+            {
+              "prompt": "A medium, eye-level shot of a small group of friends sitting on the grass in a park, chatting on a sunny afternoon. They are wearing simple t-shirts and jeans.",
+              "network_multiplier": "-1.0",
+              "seed": 42
+            },
+            {
+              "prompt": "A medium, eye-level shot of a small group of friends sitting on the grass in a park, chatting on a sunny afternoon. They are wearing simple t-shirts and jeans.",
+              "network_multiplier": "-0.5",
+              "seed": 42
+            },
+            {
+              "prompt": "A medium, eye-level shot of a small group of friends sitting on the grass in a park, chatting on a sunny afternoon. They are wearing simple t-shirts and jeans.",
+              "network_multiplier": "0.0",
+              "seed": 42
+            },
+            {
+              "prompt": "A medium, eye-level shot of a small group of friends sitting on the grass in a park, chatting on a sunny afternoon. They are wearing simple t-shirts and jeans.",
+              "network_multiplier": "0.5",
+              "seed": 42
+            },
+            {
+              "prompt": "A medium, eye-level shot of a small group of friends sitting on the grass in a park, chatting on a sunny afternoon. They are wearing simple t-shirts and jeans.",
+              "network_multiplier": "1.0",
+              "seed": 42
+            },
+            {
+              "prompt": "A medium, eye-level shot of a small group of friends sitting on the grass in a park, chatting on a sunny afternoon. They are wearing simple t-shirts and jeans.",
+              "network_multiplier": "2.0",
+              "seed": 42
+            }
+          ],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 25,
+          "num_frames": 1,
+          "fps": 1
+        },
+        "slider": {
+          "guidance_strength": 3,
+          "anchor_strength": 1,
+          "positive_prompt": "A photo of a vibrant hippie festival scene, with a joyful crowd, psychedelic tie-dye patterns, and live music.",
+          "negative_prompt": "A photo of a mundane modern scene, with organized space, plain solid colors, and a quiet atmosphere.",
+          "target_class": "scene",
+          "anchor_class": ""
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

The_Cosmic_Drift_Slider.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9269b4e11a91b3ac8a90d5f364d131eead028567f1823427b3302f2f0f5aa4
+size 73957928

The_Cosmic_Drift_Slider_000000200.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86fb5ea84b25e83c50a6bf103dd852508cf8209c84e03be80f7d4ec91d6214c
+size 73957928

The_Cosmic_Drift_Slider_000000225.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2576eebce036b38635c5b64e55ba366ff09afa52b9275b21dcfc981f9f91b489
+size 73957928

The_Cosmic_Drift_Slider_000000250.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2512e2d8c515d1e60c0eb0d6726e0809aa76b209d1f9e60962d87b8e4015fbd7
+size 73957928

The_Cosmic_Drift_Slider_000000275.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078c1c2ce2bf59a3ce4e7660ef28aa0def496b7396698138e1d46feab7480e46
+size 73957928

config.yaml

@@ -0,0 +1,142 @@
+job: extension
+config:
+  name: The_Cosmic_Drift_Slider
+  process:
+  - type: concept_slider
+    training_folder: /app/ai-toolkit/output
+    sqlite_db_path: /app/ai-toolkit/aitk_db.db
+    device: cuda
+    trigger_word: null
+    performance_log_every: 10
+    network:
+      type: lora
+      linear: 4
+      linear_alpha: 4
+      conv: 16
+      conv_alpha: 16
+      lokr_full_rank: true
+      lokr_factor: -1
+      network_kwargs:
+        ignore_if_contains: []
+    save:
+      dtype: bf16
+      save_every: 25
+      max_step_saves_to_keep: 4
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /app/ai-toolkit/datasets/the_cosmic_drift_slider
+      control_path: null
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: ''
+      caption_ext: txt
+      caption_dropout_rate: 0.05
+      cache_latents_to_disk: false
+      is_reg: false
+      network_weight: 1
+      resolution:
+      - 512
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 1
+      do_i2v: true
+      flip_x: true
+      flip_y: false
+    train:
+      batch_size: 4
+      bypass_guidance_embedding: false
+      steps: 300
+      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: true
+      cache_text_embeddings: false
+      lr: 0.001
+      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
+    model:
+      name_or_path: Qwen/Qwen-Image
+      quantize: true
+      qtype: uint3|ostris/accuracy_recovery_adapters/qwen_image_torchao_uint3.safetensors
+      quantize_te: true
+      qtype_te: qfloat8
+      arch: qwen_image
+      low_vram: true
+      model_kwargs: {}
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 1024
+      height: 1024
+      samples:
+      - prompt: A medium, eye-level shot of a small group of friends sitting on the
+          grass in a park, chatting on a sunny afternoon. They are wearing simple
+          t-shirts and jeans.
+        network_multiplier: '-2.0'
+        seed: 42
+      - prompt: A medium, eye-level shot of a small group of friends sitting on the
+          grass in a park, chatting on a sunny afternoon. They are wearing simple
+          t-shirts and jeans.
+        network_multiplier: '-1.0'
+        seed: 42
+      - prompt: A medium, eye-level shot of a small group of friends sitting on the
+          grass in a park, chatting on a sunny afternoon. They are wearing simple
+          t-shirts and jeans.
+        network_multiplier: '-0.5'
+        seed: 42
+      - prompt: A medium, eye-level shot of a small group of friends sitting on the
+          grass in a park, chatting on a sunny afternoon. They are wearing simple
+          t-shirts and jeans.
+        network_multiplier: '0.0'
+        seed: 42
+      - prompt: A medium, eye-level shot of a small group of friends sitting on the
+          grass in a park, chatting on a sunny afternoon. They are wearing simple
+          t-shirts and jeans.
+        network_multiplier: '0.5'
+        seed: 42
+      - prompt: A medium, eye-level shot of a small group of friends sitting on the
+          grass in a park, chatting on a sunny afternoon. They are wearing simple
+          t-shirts and jeans.
+        network_multiplier: '1.0'
+        seed: 42
+      - prompt: A medium, eye-level shot of a small group of friends sitting on the
+          grass in a park, chatting on a sunny afternoon. They are wearing simple
+          t-shirts and jeans.
+        network_multiplier: '2.0'
+        seed: 42
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 25
+      num_frames: 1
+      fps: 1
+    slider:
+      guidance_strength: 3
+      anchor_strength: 1
+      positive_prompt: A photo of a vibrant hippie festival scene, with a joyful crowd,
+        psychedelic tie-dye patterns, and live music.
+      negative_prompt: A photo of a mundane modern scene, with organized space, plain
+        solid colors, and a quiet atmosphere.
+      target_class: scene
+      anchor_class: ''
+meta:
+  name: The_Cosmic_Drift_Slider
+  version: '1.0'

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5098644450a8c4a0c62ac5500870544272d80e7dd3c3e15fe2e392a3923028
+size 76537549