Model card auto-generated by SimpleTuner

README.md

@@ -0,0 +1,151 @@
+---
+license: other
+base_model: "black-forest-labs/FLUX.1-dev"
+tags:
+  - flux
+  - flux-diffusers
+  - text-to-image
+  - diffusers
+  - simpletuner
+  - safe-for-work
+  - lora
+  - template:sd-lora
+  - standard
+inference: true
+widget:
+- text: 'unconditional (blank prompt)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_0_0.png
+- text: 'A scene from Chainsaw Man. Makima holding a sign that says ''I LOVE PROMPTS!'', she is standing full body on a beach at sunset. She is wearing her white button-up shirt, black tie, and black trousers. The setting sun casts a dynamic shadow on her composed and enigmatic expression.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_1_0.png
+- text: 'A scene from Chainsaw Man. Makima jumping out of a propeller airplane, sky diving. Her expression remains calm and controlled, her red hair flowing in the wind. The sky is clear and blue, with birds flying in the distance.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_2_0.png
+- text: 'A scene from Chainsaw Man. Makima spinning a basketball on her finger on a basketball court. She is wearing a Lakers jersey with the #12 on it. The basketball hoop and cheering crowd are in the background. She has a composed and confident smile.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_3_0.png
+- text: 'A scene from Chainsaw Man. Makima is wearing a professional suit in an office, shaking the hand of a businesswoman. The woman has purple hair and is wearing formal attire. There is a Google logo in the background. It is during daytime, and the overall sentiment is one of achievement and authority.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_4_0.png
+- text: 'A scene from Chainsaw Man. Makima is fighting a large brown grizzly bear, deep in a forest. The bear is tall and standing on two legs, roaring. The bear is also wearing a crown because it is the king of all bears. Around them are tall trees and other animals watching intently.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_5_0.png
+---
+
+# makima-standard-lora-1
+
+This is a standard PEFT LoRA derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev).
+
+
+No validation prompt was used during training.
+
+None
+
+
+
+## Validation settings
+- CFG: `3.5`
+- CFG Rescale: `0.0`
+- Steps: `20`
+- 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: 8
+- Training steps: 100
+- Learning rate: 0.0003
+  - Learning rate schedule: constant
+  - Warmup steps: 100
+- Max grad norm: 2.0
+- Effective batch size: 56
+  - Micro-batch size: 56
+  - Gradient accumulation steps: 1
+  - Number of GPUs: 1
+- Gradient checkpointing: True
+- Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flow_matching_loss=compatible', 'flux_lora_target=all'])
+- Optimizer: adamw_bf16
+- Trainable parameter precision: Pure BF16
+- Caption dropout probability: 0.0%
+
+
+- LoRA Rank: 128
+- LoRA Alpha: None
+- LoRA Dropout: 0.1
+- LoRA initialisation style: default
+    
+
+## Datasets
+
+### makima-512
+- Repeats: 2
+- Total number of images: 172
+- 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-dev'
+adapter_id = 'adipanda/makima-standard-lora-1'
+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 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
+image = pipeline(
+    prompt=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=1024,
+    height=1024,
+    guidance_scale=3.5,
+).images[0]
+image.save("output.png", format="PNG")
+```
+
+
+