Model card auto-generated by SimpleTuner

README.md

@@ -0,0 +1,129 @@
+---
+license: other
+base_model: "black-forest-labs/FLUX.2-klein-base-4B"
+tags:
+  - flux2
+  - flux2-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
+
+---
+
+# Andy-ML-And-AI/LIQGLASS-klein-lora
+
+This is a PEFT LoRA derived from [black-forest-labs/FLUX.2-klein-base-4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4B).
+
+The main validation prompt used during training was:
+```
+LIQGLASS, macOS Liquid Glass style icon, translucent frosted glass squircle shape, Safari browser app, compass symbol, blue tinted glass, specular highlight, inner glow, light refraction at edges, depth layering, soft shadow, Apple macOS design language, high detail
+```
+
+
+## Validation settings
+- CFG: `None`
+- CFG Rescale: `0.0`
+- Steps: `20`
+- Sampler: `FlowMatchEulerDiscreteScheduler`
+- Seed: `42`
+- Resolution: `512x512`
+
+
+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: 200
+- 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: `int8-quanto`
+- Caption dropout probability: 0.1%
+
+
+
+- LoRA Rank: 8
+- LoRA Alpha: 8.0
+- LoRA Dropout: 0.1
+- LoRA initialisation style: default
+- LoRA mode: Standard
+    
+
+## Datasets
+
+### liqglass-dataset
+- Repeats: 0
+- Total number of images: 542
+- Total number of aspect buckets: 1
+- Resolution: 0.262144 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-klein-base-4B'
+adapter_id = 'Andy-ML-And-AI/Andy-ML-And-AI/LIQGLASS-klein-lora'
+pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
+pipeline.load_lora_weights(adapter_id)
+
+prompt = "LIQGLASS, macOS Liquid Glass style icon, translucent frosted glass squircle shape, Safari browser app, compass symbol, blue tinted glass, specular highlight, inner glow, light refraction at edges, depth layering, soft shadow, Apple macOS design language, high detail"
+negative_prompt = 'ugly, flat, matte, no glass effect, blurry, low quality, old style, skeuomorphic, glossy blob, vista style'
+
+## Optional: quantise the model to save on vram.
+## Note: The model was quantised during training, and so it is recommended to do the same 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=20,
+    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
+    width=512,
+    height=512,
+    guidance_scale=None,
+).images[0]
+
+model_output.save("output.png", format="PNG")
+
+```
+
+
+