Model card auto-generated by SimpleTuner

README.md

@@ -0,0 +1,136 @@
+---
+license: apache-2.0
+base_model: "fal/AuraFlow"
+tags:
+  - auraflow
+  - auraflow-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: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_0_0.png
+- text: 'An domokun running through a field with flowers all around him.'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_1_0.png
+---
+
+# Auraflow-DomoKun-LoRA-rank8
+
+This is a standard PEFT LoRA derived from [fal/AuraFlow](https://huggingface.co/fal/AuraFlow).
+
+The main validation prompt used during training was:
+```
+An domokun running through a field with flowers all around him.
+```
+
+
+## Validation settings
+- CFG: `4.0`
+- CFG Rescale: `0.0`
+- Steps: `30`
+- Sampler: `FlowMatchEulerDiscreteScheduler`
+- Seed: `42`
+- Resolution: `512x512`
+
+
+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: 5
+- Training steps: 750
+- Learning rate: 0.0001
+  - Learning rate schedule: constant
+  - Warmup steps: 100
+- Max grad value: 0.01
+- Effective batch size: 3
+  - Micro-batch size: 1
+  - Gradient accumulation steps: 1
+  - Number of GPUs: 3
+- Gradient checkpointing: True
+- Prediction type: flow_matching (extra parameters=['shift=3'])
+- Optimizer: adamw_bf16
+- Trainable parameter precision: Pure BF16
+- Base model precision: `no_change`
+- Caption dropout probability: 10.0%
+
+
+- LoRA Rank: 8
+- LoRA Alpha: 8.0
+- LoRA Dropout: 0.1
+- LoRA initialisation style: default
+    
+
+## Datasets
+
+### domokun-cropped-512
+- Repeats: 10
+- Total number of images: ~36
+- Total number of aspect buckets: 7
+- 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 = 'fal/AuraFlow'
+adapter_id = 'bghira/Auraflow-DomoKun-LoRA-rank8'
+pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
+pipeline.load_lora_weights(adapter_id)
+
+prompt = "An domokun running through a field with flowers all around him."
+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=30,
+    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=4.0,
+).images[0]
+
+model_output.save("output.png", format="PNG")
+
+```
+
+
+