Hugging Face's logo

sin30
/
123

PyTorch
ONNX
Model card Files
xet
Community
123
File size: 2,985 Bytes 
c218334
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
 
job: extension
config:
  name: quanhuang_run
  process:
  - type: ui_trainer
    training_folder: /app/output
    sqlite_db_path: /app/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: bf16
      save_every: 250
      max_step_saves_to_keep: 4
      save_format: diffusers
      push_to_hub: false
    datasets:
    - folder_path: /app/datasets/quanhuang_target
      control_path: /app/datasets/quanhuang_control
      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
      controls: []
      shrink_video_to_frames: true
      num_frames: 1
    train:
      batch_size: 1
      bypass_guidance_embedding: false
      steps: 4000
      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
      lr: 0.0001
      ema_config:
        use_ema: false
        ema_decay: 0.99
      skip_first_sample: false
      disable_sampling: false
      dtype: bf16
      diff_output_preservation: false
      diff_output_preservation_multiplier: 1
      diff_output_preservation_class: person
    model:
      name_or_path: black-forest-labs/FLUX.1-Kontext-dev
      quantize: true
      quantize_te: true
      arch: flux_kontext
      low_vram: false
      model_kwargs: {}
    sample:
      sampler: flowmatch
      sample_every: 250
      width: 1024
      height: 1024
      prompts:
      - Transform to 90s Japanese fighting game character illustration style --ctrl_img
        /app/datasets/quanhuang_test/01.jpg
      - Transform to 90s Japanese fighting game character illustration style --ctrl_img
        /app/datasets/quanhuang_test/02.jpg
      - Transform to 90s Japanese fighting game character illustration style --ctrl_img
        /app/datasets/quanhuang_test/03.jpg
      - Transform to 90s Japanese fighting game character illustration style --ctrl_img
        /app/datasets/quanhuang_test/04.jpg
      - Transform to 90s Japanese fighting game character illustration style --ctrl_img
        /app/datasets/quanhuang_test/05.jpg
      - Transform to 90s Japanese fighting game character illustration style --ctrl_img
        /app/datasets/quanhuang_test/06.jpg
      neg: ''
      seed: 42
      walk_seed: true
      guidance_scale: 4
      sample_steps: 25
      num_frames: 1
      fps: 1
meta:
  name: quanhuang_run
  version: '1.0'