Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,98 @@ 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
+data/assets/.ipynb_checkpoints/image_0_0-checkpoint.png filter=lfs diff=lfs merge=lfs -text
+data/assets/image_0_0.png filter=lfs diff=lfs merge=lfs -text
+data/assets/image_1_0.png filter=lfs diff=lfs merge=lfs -text
+data/assets/image_2_0.png filter=lfs diff=lfs merge=lfs -text
+data/assets/image_3_0.png filter=lfs diff=lfs merge=lfs -text
+data/benchmarks/base_model/.ipynb_checkpoints/val-edited-images_0_1024x1024-checkpoint.png filter=lfs diff=lfs merge=lfs -text
+data/benchmarks/base_model/val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/benchmarks/base_model/val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/benchmarks/base_model/val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/benchmarks/base_model/val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/.ipynb_checkpoints/step_1000_val-edited-images_1_1024x1024-checkpoint.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_0_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_0_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_0_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_0_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_10000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_10000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_10000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_10000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_1000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_1000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_1000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_1000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_11000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_11000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_11000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_11000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_12000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_12000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_12000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_12000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_13000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_13000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_13000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_13000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_14000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_14000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_14000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_14000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_15000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_15000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_15000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_15000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_16000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_16000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_16000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_16000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_17000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_17000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_17000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_17000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_18000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_18000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_18000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_18000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_19000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_19000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_19000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_19000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_20000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_20000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_20000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_20000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_2000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_2000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_2000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_2000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_3000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_3000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_3000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_3000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_4000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_4000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_4000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_4000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_5000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_5000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_5000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_5000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_6000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_6000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_6000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_6000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_7000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_7000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_7000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_7000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_8000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_8000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_8000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_8000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_9000_val-edited-images_0_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_9000_val-edited-images_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_9000_val-edited-images_2_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+data/validation_images/step_9000_val-edited-images_3_1024x1024.png filter=lfs diff=lfs merge=lfs -text

data/.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,156 @@
+---
+license: other
+base_model: "black-forest-labs/FLUX.1-Kontext-dev"
+tags:
+  - flux
+  - flux-diffusers
+  - text-to-image
+  - image-to-image
+  - diffusers
+  - simpletuner
+  - not-for-all-audiences
+  - lora
+
+  - template:sd-lora
+  - standard
+pipeline_tag: text-to-image
+inference: true
+widget:
+- text: 'unconditional (blank prompt)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_0_0.png
+- text: 'prompt not found (1)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_1_0.png
+- text: 'prompt not found (2)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_2_0.png
+- text: 'prompt not found (3)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_3_0.png
+---
+
+# color-match-kontext-training
+
+This is a PEFT LoRA derived from [black-forest-labs/FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev).
+
+No validation prompt was used during training.
+
+None
+
+
+
+## Validation settings
+- CFG: `2.5`
+- CFG Rescale: `0.0`
+- Steps: `28`
+- Sampler: `FlowMatchEulerDiscreteScheduler`
+- Seed: `42`
+- Resolution: `1024x1024`
+- Skip-layer guidance: 
+
+Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
+
+You can find some example images in the following gallery:
+
+
+<Gallery />
+
+The text encoder **was not** trained.
+You may reuse the base model text encoder for inference.
+
+
+## Training settings
+
+- Training epochs: 0
+- Training steps: 20000
+- Learning rate: 1e-05
+  - Learning rate schedule: polynomial
+  - Warmup steps: 200
+- Max grad value: 2.0
+- Effective batch size: 2
+  - Micro-batch size: 2
+  - Gradient accumulation steps: 1
+  - Number of GPUs: 1
+- Gradient checkpointing: True
+- Prediction type: flow_matching (extra parameters=['flow_schedule_auto_shift', 'shift=0.0', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flux_lora_target=all'])
+- Optimizer: optimi-lion
+- Trainable parameter precision: Pure BF16
+- Base model precision: `no_change`
+- Caption dropout probability: 0.0%
+
+
+- LoRA Rank: 768
+- LoRA Alpha: None
+- LoRA Dropout: 0.1
+- LoRA initialisation style: default
+- LoRA mode: Standard
+    
+
+## Datasets
+
+### val-edited-images
+- Repeats: 0
+- Total number of images: 10
+- Total number of aspect buckets: 1
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### train-edited-images
+- Repeats: 0
+- Total number of images: 100000
+- Total number of aspect buckets: 1
+- Resolution: 0.262144 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+
+
+## Inference
+
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+
+model_id = 'black-forest-labs/FLUX.1-Kontext-dev'
+adapter_id = 'color-match-kontext-training'
+pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
+pipeline.load_lora_weights(adapter_id)
+
+prompt = "An astronaut is riding a horse through the jungles of Thailand."
+
+
+## Optional: quantise the model to save on vram.
+## Note: The model was not quantised during training, so it is not necessary to quantise it during inference time.
+#from optimum.quanto import quantize, freeze, qint8
+#quantize(pipeline.transformer, weights=qint8)
+#freeze(pipeline.transformer)
+    
+pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
+model_output = pipeline(
+    prompt=prompt,
+    num_inference_steps=28,
+    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
+    width=1024,
+    height=1024,
+    guidance_scale=2.5,
+).images[0]
+
+model_output.save("output.png", format="PNG")
+
+```
+
+
+

data/README.md

@@ -0,0 +1,156 @@
+---
+license: other
+base_model: "black-forest-labs/FLUX.1-Kontext-dev"
+tags:
+  - flux
+  - flux-diffusers
+  - text-to-image
+  - image-to-image
+  - diffusers
+  - simpletuner
+  - not-for-all-audiences
+  - lora
+
+  - template:sd-lora
+  - standard
+pipeline_tag: text-to-image
+inference: true
+widget:
+- text: 'unconditional (blank prompt)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_0_0.png
+- text: 'prompt not found (1)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_1_0.png
+- text: 'prompt not found (2)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_2_0.png
+- text: 'prompt not found (3)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_3_0.png
+---
+
+# color-match-kontext-training
+
+This is a PEFT LoRA derived from [black-forest-labs/FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev).
+
+No validation prompt was used during training.
+
+None
+
+
+
+## Validation settings
+- CFG: `2.5`
+- CFG Rescale: `0.0`
+- Steps: `28`
+- Sampler: `FlowMatchEulerDiscreteScheduler`
+- Seed: `42`
+- Resolution: `1024x1024`
+- Skip-layer guidance: 
+
+Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
+
+You can find some example images in the following gallery:
+
+
+<Gallery />
+
+The text encoder **was not** trained.
+You may reuse the base model text encoder for inference.
+
+
+## Training settings
+
+- Training epochs: 0
+- Training steps: 20000
+- Learning rate: 1e-05
+  - Learning rate schedule: polynomial
+  - Warmup steps: 200
+- Max grad value: 2.0
+- Effective batch size: 2
+  - Micro-batch size: 2
+  - Gradient accumulation steps: 1
+  - Number of GPUs: 1
+- Gradient checkpointing: True
+- Prediction type: flow_matching (extra parameters=['flow_schedule_auto_shift', 'shift=0.0', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flux_lora_target=all'])
+- Optimizer: optimi-lion
+- Trainable parameter precision: Pure BF16
+- Base model precision: `no_change`
+- Caption dropout probability: 0.0%
+
+
+- LoRA Rank: 768
+- LoRA Alpha: None
+- LoRA Dropout: 0.1
+- LoRA initialisation style: default
+- LoRA mode: Standard
+    
+
+## Datasets
+
+### val-edited-images
+- Repeats: 0
+- Total number of images: 10
+- Total number of aspect buckets: 1
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### train-edited-images
+- Repeats: 0
+- Total number of images: 100000
+- Total number of aspect buckets: 1
+- Resolution: 0.262144 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+
+
+## Inference
+
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+
+model_id = 'black-forest-labs/FLUX.1-Kontext-dev'
+adapter_id = 'color-match-kontext-training'
+pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
+pipeline.load_lora_weights(adapter_id)
+
+prompt = "An astronaut is riding a horse through the jungles of Thailand."
+
+
+## Optional: quantise the model to save on vram.
+## Note: The model was not quantised during training, so it is not necessary to quantise it during inference time.
+#from optimum.quanto import quantize, freeze, qint8
+#quantize(pipeline.transformer, weights=qint8)
+#freeze(pipeline.transformer)
+    
+pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
+model_output = pipeline(
+    prompt=prompt,
+    num_inference_steps=28,
+    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
+    width=1024,
+    height=1024,
+    guidance_scale=2.5,
+).images[0]
+
+model_output.save("output.png", format="PNG")
+
+```
+
+
+

data/all_image_files_val-edited-images.json

@@ -0,0 +1 @@
+{"/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000005.png": false, "/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000009.png": false, "/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000003.png": false, "/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000006.png": false, "/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000008.png": false, "/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000004.png": false, "/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000002.png": false, "/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000001.png": false, "/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000007.png": false, "/workspace/logo_color_match/data/logo-icons/val/edited-images/img-000000.png": false}

data/all_image_files_val-reference-images.json

@@ -0,0 +1 @@
+{"/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000009.png": false, "/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000003.png": false, "/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000008.png": false, "/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000005.png": false, "/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000004.png": false, "/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000006.png": false, "/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000001.png": false, "/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000000.png": false, "/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000002.png": false, "/workspace/logo_color_match/data/logo-icons/val/reference-images/img-000007.png": false}

data/all_vae_cache_files_train-edited-images.json

@@ -0,0 +1 @@
+{}

data/all_vae_cache_files_train-reference-images.json

@@ -0,0 +1 @@
+{}

data/all_vae_cache_files_val-edited-images.json

@@ -0,0 +1 @@
+{"/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/d0a8d8c5c9ebf7e55679d601fa688e1f4d577fd8833a695f07c368996dae2be6.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/6ab5676f80cb2908475fa3cf796faccc252ef24212c8faaf9e29a2f205b6db90.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/9598fa80366a9421938165b5f699bdaaea54ec4091d72d3f0d11947f665e5530.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/69881e6b4eed930c4e55612c2fe191d715c3eb9d3db1aa54b96bd0684e49d425.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/5dafb8dd1849bce3e069e5c4b54558db9ec62340d6dd923bd7415306ac0c8343.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/093c212d1f02bd1d8e5f19394949dfee746c299f5ef82ae0dbfb557fa9da4844.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/8988545e256e266ea8b79c50ae0b4f0e6f1f06fded901944f4016a8c50fb6671.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/1b427175668fd057273d4525f77b44e920182415f99cdd361b560ce100f62ea6.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/29634eb07d7a73ad3aa122f2a9ca6b285e432572450934802324cb851bb035ee.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/edit-images/ce8ff2eed47ff980d29ca1e5a46ad80fd6e92d3060c3c831e5dff563431aac2e.pt": false}

data/all_vae_cache_files_val-reference-images.json

@@ -0,0 +1 @@
+{"/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/69881e6b4eed930c4e55612c2fe191d715c3eb9d3db1aa54b96bd0684e49d425.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/5dafb8dd1849bce3e069e5c4b54558db9ec62340d6dd923bd7415306ac0c8343.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/6ab5676f80cb2908475fa3cf796faccc252ef24212c8faaf9e29a2f205b6db90.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/ce8ff2eed47ff980d29ca1e5a46ad80fd6e92d3060c3c831e5dff563431aac2e.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/8988545e256e266ea8b79c50ae0b4f0e6f1f06fded901944f4016a8c50fb6671.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/d0a8d8c5c9ebf7e55679d601fa688e1f4d577fd8833a695f07c368996dae2be6.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/9598fa80366a9421938165b5f699bdaaea54ec4091d72d3f0d11947f665e5530.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/1b427175668fd057273d4525f77b44e920182415f99cdd361b560ce100f62ea6.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/093c212d1f02bd1d8e5f19394949dfee746c299f5ef82ae0dbfb557fa9da4844.pt": false, "/workspace/logo_color_match/data/logo-icons/val/cache/vae/flux/kontext/ref-images/29634eb07d7a73ad3aa122f2a9ca6b285e432572450934802324cb851bb035ee.pt": false}

data/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e0a0ae10a77cdca1fe6813ab803c272f012d075b05b29b8b29db46854a594e
+size 1434478448

data/simpletuner_config.json

@@ -0,0 +1,318 @@
+{
+    "snr_gamma": null,
+    "use_soft_min_snr": false,
+    "soft_min_snr_sigma_data": null,
+    "model_family": "flux",
+    "model_flavour": "kontext",
+    "model_type": "lora",
+    "loss_type": "l2",
+    "huber_schedule": "snr",
+    "huber_c": 0.1,
+    "hidream_use_load_balancing_loss": false,
+    "hidream_load_balancing_loss_weight": null,
+    "flux_lora_target": "all",
+    "flow_sigmoid_scale": 1.0,
+    "flux_fast_schedule": false,
+    "flow_use_uniform_schedule": false,
+    "flow_use_beta_schedule": false,
+    "flow_beta_schedule_alpha": 2.0,
+    "flow_beta_schedule_beta": 2.0,
+    "flow_schedule_shift": 0.0,
+    "flow_schedule_auto_shift": true,
+    "flux_guidance_mode": "constant",
+    "flux_guidance_value": 1.0,
+    "flux_guidance_min": 0.0,
+    "flux_guidance_max": 4.0,
+    "flux_attention_masked_training": false,
+    "ltx_train_mode": "i2v",
+    "ltx_i2v_prob": 0.1,
+    "ltx_protect_first_frame": false,
+    "ltx_partial_noise_fraction": 0.05,
+    "t5_padding": "unmodified",
+    "sd3_clip_uncond_behaviour": "empty_string",
+    "sd3_t5_uncond_behaviour": null,
+    "lora_type": "standard",
+    "peft_lora_mode": "standard",
+    "singlora_ramp_up_steps": 0,
+    "lora_init_type": "default",
+    "init_lora": null,
+    "lora_rank": 768,
+    "lora_alpha": null,
+    "lora_dropout": 0.1,
+    "lycoris_config": "config/lycoris_config.json",
+    "init_lokr_norm": null,
+    "conditioning_multidataset_sampling": "random",
+    "control": false,
+    "controlnet": false,
+    "controlnet_custom_config": null,
+    "tread_config": null,
+    "controlnet_model_name_or_path": null,
+    "pretrained_model_name_or_path": "black-forest-labs/FLUX.1-Kontext-dev",
+    "pretrained_transformer_model_name_or_path": null,
+    "pretrained_transformer_subfolder": "transformer",
+    "pretrained_unet_model_name_or_path": null,
+    "pretrained_unet_subfolder": "unet",
+    "pretrained_vae_model_name_or_path": "black-forest-labs/FLUX.1-Kontext-dev",
+    "pretrained_t5_model_name_or_path": null,
+    "prediction_type": null,
+    "snr_weight": 1.0,
+    "training_scheduler_timestep_spacing": "trailing",
+    "inference_scheduler_timestep_spacing": "trailing",
+    "refiner_training": false,
+    "refiner_training_invert_schedule": false,
+    "refiner_training_strength": 0.2,
+    "timestep_bias_strategy": "none",
+    "timestep_bias_multiplier": 1.0,
+    "timestep_bias_begin": 0,
+    "timestep_bias_end": 1000,
+    "timestep_bias_portion": 0.25,
+    "disable_segmented_timestep_sampling": false,
+    "rescale_betas_zero_snr": false,
+    "vae_dtype": "bf16",
+    "vae_batch_size": 4,
+    "vae_enable_tiling": false,
+    "vae_enable_slicing": false,
+    "vae_cache_scan_behaviour": "recreate",
+    "vae_cache_ondemand": false,
+    "compress_disk_cache": false,
+    "aspect_bucket_disable_rebuild": false,
+    "keep_vae_loaded": false,
+    "skip_file_discovery": "",
+    "revision": null,
+    "variant": null,
+    "preserve_data_backend_cache": false,
+    "use_dora": false,
+    "override_dataset_config": false,
+    "cache_dir_text": "cache",
+    "cache_dir_vae": "",
+    "data_backend_config": "config/multidatabackend.json",
+    "data_backend_sampling": "auto-weighting",
+    "ignore_missing_files": false,
+    "write_batch_size": 128,
+    "read_batch_size": 25,
+    "image_processing_batch_size": 32,
+    "enable_multiprocessing": false,
+    "max_workers": 32,
+    "aws_max_pool_connections": 128,
+    "torch_num_threads": 8,
+    "dataloader_prefetch": false,
+    "dataloader_prefetch_qlen": 10,
+    "aspect_bucket_worker_count": 12,
+    "cache_dir": "output/models/cache",
+    "cache_clear_validation_prompts": false,
+    "caption_strategy": "filename",
+    "parquet_caption_column": null,
+    "parquet_filename_column": null,
+    "instance_prompt": null,
+    "output_dir": "output/models",
+    "seed": 42,
+    "seed_for_each_device": true,
+    "framerate": null,
+    "resolution": 1024,
+    "resolution_type": "pixel_area",
+    "aspect_bucket_rounding": 2,
+    "aspect_bucket_alignment": 64,
+    "minimum_image_size": null,
+    "maximum_image_size": null,
+    "target_downsample_size": null,
+    "train_text_encoder": false,
+    "tokenizer_max_length": 512,
+    "train_batch_size": 2,
+    "num_train_epochs": 1,
+    "max_train_steps": 20000,
+    "ignore_final_epochs": false,
+    "checkpointing_steps": 1000,
+    "checkpointing_rolling_steps": 0,
+    "checkpointing_use_tempdir": false,
+    "checkpoints_total_limit": 20,
+    "checkpoints_rolling_total_limit": 1,
+    "resume_from_checkpoint": null,
+    "gradient_accumulation_steps": 1,
+    "gradient_checkpointing": true,
+    "gradient_checkpointing_interval": null,
+    "learning_rate": 1e-05,
+    "text_encoder_lr": null,
+    "lr_scale": false,
+    "lr_scale_sqrt": false,
+    "lr_scheduler": "polynomial",
+    "lr_warmup_steps": 200,
+    "lr_num_cycles": 1,
+    "lr_power": 0.8,
+    "distillation_method": null,
+    "distillation_config": null,
+    "use_ema": false,
+    "ema_device": "cpu",
+    "ema_validation": "comparison",
+    "ema_cpu_only": false,
+    "ema_foreach_disable": false,
+    "ema_update_interval": null,
+    "ema_decay": 0.995,
+    "non_ema_revision": null,
+    "offload_during_startup": false,
+    "offload_param_path": null,
+    "optimizer": "optimi-lion",
+    "optimizer_config": null,
+    "optimizer_cpu_offload_method": "none",
+    "optimizer_offload_gradients": false,
+    "fuse_optimizer": false,
+    "optimizer_beta1": null,
+    "optimizer_beta2": null,
+    "optimizer_release_gradients": false,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_weight_decay": 0.01,
+    "adam_epsilon": 1e-08,
+    "prodigy_steps": null,
+    "max_grad_norm": 2.0,
+    "grad_clip_method": "value",
+    "push_to_hub": false,
+    "push_checkpoints_to_hub": false,
+    "hub_model_id": null,
+    "model_card_note": null,
+    "model_card_safe_for_work": false,
+    "logging_dir": "output/models/logs",
+    "disable_benchmark": false,
+    "evaluation_type": null,
+    "eval_dataset_pooling": false,
+    "pretrained_evaluation_model_name_or_path": "openai/clip-vit-large-patch14-336",
+    "validation_on_startup": false,
+    "validation_seed_source": "cpu",
+    "validation_lycoris_strength": 1.0,
+    "validation_torch_compile": false,
+    "validation_torch_compile_mode": "max-autotune",
+    "validation_guidance_skip_layers": null,
+    "validation_guidance_skip_layers_start": 0.01,
+    "validation_guidance_skip_layers_stop": 0.2,
+    "validation_guidance_skip_scale": 2.8,
+    "sana_complex_human_instruction": [
+        "Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:",
+        "- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.",
+        "- Do not add detail that is not in the original prompt! Do not mention colors if the User Prompt does not!",
+        "- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.",
+        "- If the prompt contains explicit material, do not remove this information from the output, which would damage the performance of downstream classifiers.",
+        "Here are examples of how to transform or refine prompts:",
+        "- User Prompt: A cat sleeping -> Enhanced: A cat sleeping peacefully, showcasing the joy of pet ownership. Cute floof kitty cat gatto.",
+        "- User Prompt: A busy city street -> Enhanced: A bustling city street scene featuring a crowd of people.",
+        "Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:",
+        "User Prompt: "
+    ],
+    "disable_tf32": false,
+    "validation_using_datasets": null,
+    "webhook_config": null,
+    "webhook_reporting_interval": null,
+    "report_to": "wandb",
+    "tracker_run_name": "test",
+    "tracker_project_name": "color-match-kontext-training",
+    "tracker_image_layout": "gallery",
+    "validation_prompt": null,
+    "validation_prompt_library": false,
+    "user_prompt_library": null,
+    "validation_negative_prompt": "blurry, cropped, ugly",
+    "num_validation_images": 1,
+    "validation_disable": false,
+    "validation_steps": 1000,
+    "validation_stitch_input_location": "left",
+    "eval_steps_interval": null,
+    "eval_timesteps": 28,
+    "num_eval_images": 4,
+    "eval_dataset_id": "val-edited-images",
+    "validation_num_inference_steps": 28,
+    "validation_num_video_frames": null,
+    "validation_resolution": "1024x1024",
+    "validation_noise_scheduler": null,
+    "validation_disable_unconditional": false,
+    "enable_watermark": false,
+    "mixed_precision": "bf16",
+    "gradient_precision": null,
+    "quantize_via": "accelerator",
+    "base_model_precision": "no_change",
+    "quantize_activations": false,
+    "base_model_default_dtype": "bf16",
+    "text_encoder_1_precision": "no_change",
+    "text_encoder_2_precision": "no_change",
+    "text_encoder_3_precision": "no_change",
+    "text_encoder_4_precision": "no_change",
+    "local_rank": -1,
+    "fuse_qkv_projections": true,
+    "attention_mechanism": "diffusers",
+    "sageattention_usage": "inference",
+    "set_grads_to_none": false,
+    "noise_offset": 0.1,
+    "noise_offset_probability": 0.25,
+    "masked_loss_probability": 1.0,
+    "validation_guidance": 2.5,
+    "validation_guidance_real": 1.0,
+    "validation_no_cfg_until_timestep": 2,
+    "validation_guidance_rescale": 0.0,
+    "validation_randomize": false,
+    "validation_seed": 42,
+    "fully_unload_text_encoder": false,
+    "freeze_encoder_before": 12,
+    "freeze_encoder_after": 17,
+    "freeze_encoder_strategy": "after",
+    "layer_freeze_strategy": "none",
+    "unet_attention_slice": false,
+    "print_filenames": false,
+    "print_sampler_statistics": false,
+    "metadata_update_interval": 3600,
+    "debug_aspect_buckets": false,
+    "debug_dataset_loader": false,
+    "freeze_encoder": true,
+    "save_text_encoder": false,
+    "text_encoder_limit": 25,
+    "prepend_instance_prompt": false,
+    "only_instance_prompt": false,
+    "data_aesthetic_score": 7.0,
+    "sdxl_refiner_uses_full_range": false,
+    "caption_dropout_probability": 0.0,
+    "delete_unwanted_images": false,
+    "delete_problematic_images": false,
+    "disable_bucket_pruning": false,
+    "offset_noise": false,
+    "input_perturbation": 0.0,
+    "input_perturbation_steps": 0,
+    "lr_end": "4e-7",
+    "i_know_what_i_am_doing": false,
+    "accelerator_cache_clear_interval": null,
+    "vae_path": "black-forest-labs/FLUX.1-Kontext-dev",
+    "accelerator_project_config": {
+        "project_dir": "output/models",
+        "logging_dir": "output/models/logs",
+        "automatic_checkpoint_naming": false,
+        "total_limit": null,
+        "iteration": 20,
+        "save_on_each_node": false
+    },
+    "process_group_kwargs": {
+        "backend": "nccl",
+        "init_method": null,
+        "timeout": "1:30:00"
+    },
+    "is_quantized": false,
+    "weight_dtype": "torch.bfloat16",
+    "disable_accelerator": false,
+    "lora_initialisation_style": true,
+    "model_type_label": "Flux.1",
+    "use_deepspeed_optimizer": false,
+    "use_deepspeed_scheduler": false,
+    "base_weight_dtype": "torch.bfloat16",
+    "is_quanto": false,
+    "is_torchao": false,
+    "is_bnb": false,
+    "flow_matching": true,
+    "vae_kwargs": {
+        "pretrained_model_name_or_path": "black-forest-labs/FLUX.1-Kontext-dev",
+        "subfolder": "vae",
+        "revision": null,
+        "force_upcast": false,
+        "variant": null
+    },
+    "enable_adamw_bf16": true,
+    "overrode_max_train_steps": false,
+    "total_num_batches": 50005,
+    "num_update_steps_per_epoch": 50005,
+    "total_batch_size": 2,
+    "is_schedulefree": false,
+    "is_lr_scheduler_disabled": false,
+    "total_steps_remaining_at_start": 20000
+}