Update README.md

README.md

@@ -1,31 +1,116 @@
 ---
+license: creativeml-openrail-m
+base_model: "black-forest-labs/FLUX.1-dev"
 tags:
+  - stable-diffusion
+  - stable-diffusion-diffusers
   - text-to-image
-  - lora
   - diffusers
-  - template:diffusion-lora
+  - simpletuner
+  - lora
+  - template:sd-lora
+inference: true
 widget:
-- text: intertwined paternal voids form a goat melted into fractals crackeds.
+- text: 'unconditional (blank prompt)'
   parameters:
-    negative_prompt: blurry, bad anatomy
+    negative_prompt: ''''
   output:
-    url: images/fadfea894bb82a4b3385f13f782c39f5.jpg
-base_model: black-forest-labs/FLUX.1-dev
-instance_prompt: evil
-
+    url: .images/fadfea894bb82a4b3385f13f782c39f5.jpg
+- text: 'anime illustraion of a group photo of ddadvege and ooozar together'
+  parameters:
+    negative_prompt: ''''
+  output:
+    url: .images/fadfea894bb82a4b3385f13f782c39f5.jpg
 ---
-# Trasher
+
+# flux-lora-training
+
+This is a LoRA derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev).
+
+
+
+The main validation prompt used during training was:
+
+
+
+```
+anime illustraion of a group photo of ddadvege and ooozar together
+```
+
+## Validation settings
+- CFG: `3.5`
+- CFG Rescale: `0.0`
+- Steps: `15`
+- Sampler: `None`
+- Seed: `42`
+- Resolution: `512`
+
+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: 2999
+- Training steps: 9000
+- Learning rate: 0.0001
+- Effective batch size: 1
+  - Micro-batch size: 1
+  - Gradient accumulation steps: 1
+  - Number of GPUs: 1
+- Prediction type: flow-matching
+- Rescaled betas zero SNR: False
+- Optimizer: AdamW, stochastic bf16
+- Precision: Pure BF16
+- Xformers: Enabled
+- LoRA Rank: 32
+- LoRA Alpha: None
+- LoRA Dropout: 0.1
+- LoRA initialisation style: default
+
+
+## Datasets
+
+### default_dataset
+- Repeats: 0
+- Total number of images: 3
+- Total number of aspect buckets: 1
+- Resolution: 0.5 megapixels
+- Cropped: True
+- Crop style: center
+- Crop aspect: square
+
+
+## Inference
 
-## Trigger words
 
-You should use `evil` to trigger the image generation.
+```python
+import torch
+from diffusers import DiffusionPipeline
 
+model_id = 'black-forest-labs/FLUX.1-dev'
+adapter_id = 'Emuixom/Trasher_Riddick'
+pipeline = DiffusionPipeline.from_pretrained(model_id)
+pipeline.load_lora_weights(adapter_id)
 
-## Download model
+prompt = "anime illustraion of a group photo of ddadvege and ooozar together"
 
-Weights for this model are available in Safetensors format.
 
-[Download](/Emuixom/Trasher_Riddick/tree/main) them in the Files & versions tab.
+pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
+image = pipeline(
+    prompt=prompt,
+    num_inference_steps=15,
+    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
+    width=512,
+    height=512,
+    guidance_scale=3.5,
+).images[0]
+image.save("output.png", format="PNG")
+```