diff --git a/.job_config.json b/.job_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e10d3ad1b372652e7752a64591eb8728f860973e --- /dev/null +++ b/.job_config.json @@ -0,0 +1,135 @@ +{ + "job": "extension", + "config": { + "name": "strawbyte_v1", + "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": "bf16", + "save_every": 250, + "max_step_saves_to_keep": 4, + "save_format": "diffusers", + "push_to_hub": false + }, + "datasets": [ + { + "folder_path": "/app/ai-toolkit/datasets/strawbyte", + "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, + "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": "Qwen/Qwen-Image", + "quantize": true, + "qtype": "qfloat8", + "quantize_te": true, + "qtype_te": "qfloat8", + "arch": "qwen_image", + "low_vram": true, + "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": "ultra-realistic portrait of a young white male with short silver hair, pale skin, light stubble, and calm expression, wearing a dark modern shirt in a neutral soft-lit studio, clean background, natural shadows, very clear facial details, no props, no accessories, centered composition" + }, + { + "prompt": "realistic image of a young white male with short silver hair and pale skin passed out in a simple living room, slumped sideways on a couch, head drooped, one arm hanging down, dim warm lighting, empty drink cans on the floor, messy table nearby, soft shadows, cinematic realism" + }, + { + "prompt": "clean black-and-white line-art drawing of a young white male with short silver hair, medium shot from the waist up, minimalistic sketch style, plain white background, clean outlines, no shading, no color, consistent proportions, manga-influenced but realistic structure" + }, + { + "prompt": "full-body shot of a young white male with short silver hair standing in a minimal futuristic room, relaxed posture with arms at his sides, soft diffused lighting, clean bright background, simple clothing, no props, high clarity, neutral expression, realistic modern photography" + } + ], + "neg": "", + "seed": 42, + "walk_seed": true, + "guidance_scale": 4, + "sample_steps": 25, + "num_frames": 1, + "fps": 1 + } + } + ] + }, + "meta": { + "name": "[name]", + "version": "1.0" + } +} \ No newline at end of file diff --git a/config.yaml b/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..037e6ef11bc20483931e78f233bc24bcee0e945c --- /dev/null +++ b/config.yaml @@ -0,0 +1,119 @@ +job: extension +config: + name: strawbyte_v1 + 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: bf16 + save_every: 250 + max_step_saves_to_keep: 4 + save_format: diffusers + push_to_hub: false + datasets: + - folder_path: /app/ai-toolkit/datasets/strawbyte + 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 + 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: Qwen/Qwen-Image + quantize: true + qtype: qfloat8 + quantize_te: true + qtype_te: qfloat8 + arch: qwen_image + low_vram: true + 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: ultra-realistic portrait of a young white male with short silver hair, + pale skin, light stubble, and calm expression, wearing a dark modern shirt + in a neutral soft-lit studio, clean background, natural shadows, very clear + facial details, no props, no accessories, centered composition + - prompt: realistic image of a young white male with short silver hair and pale + skin passed out in a simple living room, slumped sideways on a couch, head + drooped, one arm hanging down, dim warm lighting, empty drink cans on the + floor, messy table nearby, soft shadows, cinematic realism + - prompt: clean black-and-white line-art drawing of a young white male with + short silver hair, medium shot from the waist up, minimalistic sketch style, + plain white background, clean outlines, no shading, no color, consistent + proportions, manga-influenced but realistic structure + - prompt: full-body shot of a young white male with short silver hair standing + in a minimal futuristic room, relaxed posture with arms at his sides, soft + diffused lighting, clean bright background, simple clothing, no props, high + clarity, neutral expression, realistic modern photography + neg: '' + seed: 42 + walk_seed: true + guidance_scale: 4 + sample_steps: 25 + num_frames: 1 + fps: 1 +meta: + name: strawbyte_v1 + version: '1.0' diff --git a/log.txt b/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..a8a8cd6b6a9e11553aa4736822f0cc07bb053f59 --- /dev/null +++ b/log.txt @@ -0,0 +1,370 @@ +Running 1 job +{ + "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": "bf16", + "save_every": 250, + "max_step_saves_to_keep": 4, + "save_format": "diffusers", + "push_to_hub": false + }, + "datasets": [ + { + "folder_path": "/app/ai-toolkit/datasets/strawbyte", + "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, + "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": "Qwen/Qwen-Image", + "quantize": true, + "qtype": "qfloat8", + "quantize_te": true, + "qtype_te": "qfloat8", + "arch": "qwen_image", + "low_vram": true, + "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": "ultra-realistic portrait of a young white male with short silver hair, pale skin, light stubble, and calm expression, wearing a dark modern shirt in a neutral soft-lit studio, clean background, natural shadows, very clear facial details, no props, no accessories, centered composition" + }, + { + "prompt": "realistic image of a young white male with short silver hair and pale skin passed out in a simple living room, slumped sideways on a couch, head drooped, one arm hanging down, dim warm lighting, empty drink cans on the floor, messy table nearby, soft shadows, cinematic realism" + }, + { + "prompt": "clean black-and-white line-art drawing of a young white male with short silver hair, medium shot from the waist up, minimalistic sketch style, plain white background, clean outlines, no shading, no color, consistent proportions, manga-influenced but realistic structure" + }, + { + "prompt": "full-body shot of a young white male with short silver hair standing in a minimal futuristic room, relaxed posture with arms at his sides, soft diffused lighting, clean bright background, simple clothing, no props, high clarity, neutral expression, realistic modern photography" + } + ], + "neg": "", + "seed": 42, + "walk_seed": true, + "guidance_scale": 4, + "sample_steps": 25, + "num_frames": 1, + "fps": 1 + } +} +Using SQLite database at /app/ai-toolkit/aitk_db.db +Job ID: "e7a6ee7f-694e-41eb-9f9a-c0153e406f89" + +############################################# +# Running job: strawbyte_v1 +############################################# + + +Running 1 process +Loading Qwen Image model +Loading transformer + Loading checkpoint shards: 0%| | 0/9 [00:00