Upload folder using huggingface_hub

.job_config.json

@@ -0,0 +1,155 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "fp32prolookv2",
+    "process": [
+      {
+        "type": "diffusion_trainer",
+        "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": 32,
+          "linear_alpha": 32,
+          "conv": 16,
+          "conv_alpha": 16,
+          "lokr_full_rank": true,
+          "lokr_factor": -1,
+          "network_kwargs": {
+            "ignore_if_contains": []
+          }
+        },
+        "save": {
+          "dtype": "fp32",
+          "save_every": 398,
+          "max_step_saves_to_keep": 100000,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/app/ai-toolkit/datasets/prolookv2",
+            "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,
+              768,
+              1024,
+              1280,
+              1536
+            ],
+            "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": 25000,
+          "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": true,
+          "lr": 0.0001,
+          "ema_config": {
+            "use_ema": false,
+            "ema_decay": 0.99
+          },
+          "skip_first_sample": true,
+          "force_first_sample": false,
+          "disable_sampling": true,
+          "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": "Qwen/Qwen-Image",
+          "quantize": true,
+          "qtype": "qfloat8",
+          "quantize_te": true,
+          "qtype_te": "qfloat8",
+          "arch": "qwen_image",
+          "low_vram": false,
+          "model_kwargs": {},
+          "layer_offloading": false,
+          "layer_offloading_text_encoder_percent": 1,
+          "layer_offloading_transformer_percent": 1
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "width": 1024,
+          "height": 1024,
+          "samples": [
+            {
+              "prompt": "woman with red hair, playing chess at the park, bomb going off in the background"
+            },
+            {
+              "prompt": "a woman holding a coffee cup, in a beanie, sitting at a cafe"
+            },
+            {
+              "prompt": "a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini"
+            },
+            {
+              "prompt": "a man showing off his cool new t shirt at the beach, a shark is jumping out of the water in the background"
+            },
+            {
+              "prompt": "a bear building a log cabin in the snow covered mountains"
+            },
+            {
+              "prompt": "woman playing the guitar, on stage, singing a song, laser lights, punk rocker"
+            },
+            {
+              "prompt": "hipster man with a beard, building a chair, in a wood shop"
+            },
+            {
+              "prompt": "photo of a man, white background, medium shot, modeling clothing, studio lighting, white backdrop"
+            },
+            {
+              "prompt": "a man holding a sign that says, 'this is a sign'"
+            },
+            {
+              "prompt": "a bulldog, in a post apocalyptic world, with a shotgun, in a leather jacket, in a desert, with a motorcycle"
+            }
+          ],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 25,
+          "num_frames": 1,
+          "fps": 1
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

config.yaml

@@ -0,0 +1,121 @@
+job: extension
+config:
+  name: fp32prolookv2
+  process:
+  - type: diffusion_trainer
+    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: 32
+      linear_alpha: 32
+      conv: 16
+      conv_alpha: 16
+      lokr_full_rank: true
+      lokr_factor: -1
+      network_kwargs:
+        ignore_if_contains: []
+    save:
+      dtype: fp32
+      save_every: 398
+      max_step_saves_to_keep: 100000
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /app/ai-toolkit/datasets/prolookv2
+      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
+      - 768
+      - 1024
+      - 1280
+      - 1536
+      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: 25000
+      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: true
+      lr: 0.0001
+      ema_config:
+        use_ema: false
+        ema_decay: 0.99
+      skip_first_sample: true
+      force_first_sample: false
+      disable_sampling: true
+      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: Qwen/Qwen-Image
+      quantize: true
+      qtype: qfloat8
+      quantize_te: true
+      qtype_te: qfloat8
+      arch: qwen_image
+      low_vram: false
+      model_kwargs: {}
+      layer_offloading: false
+      layer_offloading_text_encoder_percent: 1
+      layer_offloading_transformer_percent: 1
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 1024
+      height: 1024
+      samples:
+      - prompt: woman with red hair, playing chess at the park, bomb going off in
+          the background
+      - prompt: a woman holding a coffee cup, in a beanie, sitting at a cafe
+      - prompt: a horse is a DJ at a night club, fish eye lens, smoke machine, lazer
+          lights, holding a martini
+      - prompt: a man showing off his cool new t shirt at the beach, a shark is jumping
+          out of the water in the background
+      - prompt: a bear building a log cabin in the snow covered mountains
+      - prompt: woman playing the guitar, on stage, singing a song, laser lights,
+          punk rocker
+      - prompt: hipster man with a beard, building a chair, in a wood shop
+      - prompt: photo of a man, white background, medium shot, modeling clothing,
+          studio lighting, white backdrop
+      - prompt: a man holding a sign that says, 'this is a sign'
+      - prompt: a bulldog, in a post apocalyptic world, with a shotgun, in a leather
+          jacket, in a desert, with a motorcycle
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 25
+      num_frames: 1
+      fps: 1
+meta:
+  name: fp32prolookv2
+  version: '1.0'

fp32prolookv2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd5c0188c26c524fe4869054f239214faf8e72ee1f4f71843c135378a0a9e47
+size 1179881960

fp32prolookv2_000015124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21214283813633d5837da43545cbe0cfc9c5902deb1fc48de04bd3fa4f2caa7d
+size 1179881960

fp32prolookv2_000015522.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9616939a63e2c184ff5252bce102ce1217b54dabe24cc378d19206d8c62b356d
+size 1179881960

fp32prolookv2_000015920.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e7a04b53262c6f6c9e0b21cf9d4348009a057f6ae48053a9c5c3fb4c8dcf050
+size 1179881960

fp32prolookv2_000016318.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb73bf82d95366cfbed3311e6f9674938c1c2439601c6fe27daa6ea9a153bb6
+size 1179881960

fp32prolookv2_000016716.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516e12d780743437daf51b0c23a60d88f7c6917299ec4d893ede1a3a75246b4f
+size 1179881960

fp32prolookv2_000017114.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1490698d97d19b4e614fce84dee821efef6b1d53d82743456544b3ceeab360c5
+size 1179881960

fp32prolookv2_000017512.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620838b1042df2000c27bb3b57d45b867d00c68cff167a728558a73272ffa873
+size 1179881960

fp32prolookv2_000017910.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5de6733543314ab2c797951009ada206804eaaa11afeafdbd9937b3c653ad10d
+size 1179881960

fp32prolookv2_000018308.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5892bbc4d563fdf29f62e37c45e42ca0e500b837e656a6ce89906cd46f01cc3
+size 1179881960

fp32prolookv2_000018706.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4d9d6b44d239f48a948050044872aee91370e4a91b2317cea0957b247c8db2
+size 1179881960

fp32prolookv2_000019104.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6639617a4a858847d9b87d1734eacbfe2604cee30031b29920f3240b91c79ac
+size 1179881960

fp32prolookv2_000019502.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0360347ce3153a04edeb7396c32b7b7d7980434965a3294ebfd83f1eabe27903
+size 1179881960

fp32prolookv2_000019900.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4441c094928889f729e714f39fedf78af6cb50018e6bd7eaeaa3455e84abc1
+size 1179881960

fp32prolookv2_000020298.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b37ea1eabc5f5f13107d07f4ac0ed131152eb74e6d5c5f831949caa122aa93
+size 1179881960

fp32prolookv2_000020696.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084de87769339e5dbed1b611a1839b818f5c05e3353238aad58ad736e868f914
+size 1179881960

fp32prolookv2_000021094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d58dc911ffb998dfb10a4fc9ddcdedcb94e4308631f89570a1ba96c920c5327
+size 1179881960

fp32prolookv2_000021492.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9bdca38bc25173b71481c6b3a65f8a7c365e5bcf9a5b549a4a8ef2b79efa8a5
+size 1179881960

fp32prolookv2_000021890.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49561654eaa5efe21a7ff74a666eca5309163f92fbed704d6832a661958e0f28
+size 1179881960

fp32prolookv2_000022288.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b97ea43e457b6a73304b7ac1283347cbe542e938ff6c3c6cc9fbf42d25105b
+size 1179881960

fp32prolookv2_000022686.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c13a88fd0fccb427a913173e008eaf2181d3ada707b3923840eb93bf980067
+size 1179881960

fp32prolookv2_000023084.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef838afc71088820b066474c9a5172dc601d47409fc491987a701905414da2bd
+size 1179881960

fp32prolookv2_000023482.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e83df547903055494c73575768b888f3ec57f350b2f6f7bb19fb08d0e33bf30
+size 1179881960

fp32prolookv2_000023880.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6595cb8dab74d408a6899ece04478ad9da3cba868276c0446e38061076e67c
+size 1179881960

fp32prolookv2_000024278.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ca662f566a7a3b5edc01b0c1de3cf08d7724a1ed50a9dd143b19a9ef457a02
+size 1179881960

fp32prolookv2_000024676.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db26b47113e002fff8f72d17e99bc04d4d1c093ebf8b0c46b7544553ce13019c
+size 1179881960

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04ae3efbaaeb009889365f1e818cc535b948e7ef39e036c778824f4ce634a5a
+size 598613389

pid.txt

@@ -0,0 +1 @@
+1493