Model card auto-generated by SimpleTuner

README.md

@@ -0,0 +1,210 @@
+---
+license: other
+base_model: "black-forest-labs/FLUX.2-dev"
+tags:
+  - flux2
+  - flux2-diffusers
+  - text-to-image
+  - image-to-image
+  - diffusers
+  - simpletuner
+  - safe-for-work
+  - lora
+
+  - template:sd-lora
+  - standard
+pipeline_tag: text-to-image
+inference: true
+
+---
+
+# quzo/textf22
+
+This is a PEFT LoRA derived from [black-forest-labs/FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev).
+
+The main validation prompt used during training was:
+```
+🟫 man is holding a sign that says hello world from flux2
+```
+
+
+## Validation settings
+- CFG: `4.0`
+- CFG Rescale: `0.0`
+- Steps: `16`
+- Sampler: `FlowMatchEulerDiscreteScheduler`
+- Seed: `42`
+- Resolution: `1024x1024`
+
+
+Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
+
+
+
+
+<Gallery />
+
+The text encoder **was not** trained.
+You may reuse the base model text encoder for inference.
+
+
+## Training settings
+
+- Training epochs: 0
+- Training steps: 600
+- Learning rate: 0.0001
+  - Learning rate schedule: constant
+  - Warmup steps: 0
+- Max grad value: 2.0
+- Effective batch size: 1
+  - Micro-batch size: 1
+  - Gradient accumulation steps: 1
+  - Number of GPUs: 1
+- Gradient checkpointing: True
+- Prediction type: flow_matching[]
+- Optimizer: adamw_bf16
+- Trainable parameter precision: Pure BF16
+- Base model precision: `no_change`
+- Caption dropout probability: 0.1%
+
+
+
+- LoRA Rank: 32
+- LoRA Alpha: None
+- LoRA Dropout: 0.1
+- LoRA initialisation style: default
+- LoRA mode: Standard
+    
+
+## Datasets
+
+### emi-256
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 3
+- Resolution: 0.065536 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### emi-crop-256
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 2
+- Resolution: 0.065536 megapixels
+- Cropped: True
+- Crop style: center
+- Crop aspect: square
+- Used for regularisation data: No
+### emi-512
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 3
+- Resolution: 0.262144 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### emi-crop-512
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 2
+- Resolution: 0.262144 megapixels
+- Cropped: True
+- Crop style: center
+- Crop aspect: square
+- Used for regularisation data: No
+### emi-768
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 1
+- Resolution: 0.589824 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### emi-crop-768
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 2
+- Resolution: 0.589824 megapixels
+- Cropped: True
+- Crop style: center
+- Crop aspect: square
+- Used for regularisation data: No
+### emi-1024
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 2
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### emi-crop-1024
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 2
+- Resolution: 1.048576 megapixels
+- Cropped: True
+- Crop style: center
+- Crop aspect: square
+- Used for regularisation data: No
+### emi-1440
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 2
+- Resolution: 2.0736 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### emi-crop-1440
+- Repeats: 10
+- Total number of images: 10
+- Total number of aspect buckets: 2
+- Resolution: 2.0736 megapixels
+- Cropped: True
+- Crop style: center
+- Crop aspect: square
+- Used for regularisation data: No
+
+
+## Inference
+
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+
+model_id = 'black-forest-labs/FLUX.2-dev'
+adapter_id = 'quzo/quzo/textf22'
+pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
+pipeline.load_lora_weights(adapter_id)
+
+prompt = "🟫 man is holding a sign that says hello world from flux2"
+negative_prompt = 'ugly, cropped, blurry, low-quality, mediocre average'
+
+## 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,
+    negative_prompt=negative_prompt,
+    num_inference_steps=16,
+    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=4.0,
+).images[0]
+
+model_output.save("output.png", format="PNG")
+
+```
+
+
+