Model card auto-generated by SimpleTuner

README.md

@@ -1,9 +1,9 @@
 ---
 license: other
-base_model: "stabilityai/stable-diffusion-3-medium-diffusers"
+base_model: "black-forest-labs/FLUX.1-dev"
 tags:
-  - sd3
-  - sd3-diffusers
+  - flux
+  - flux-diffusers
   - text-to-image
   - diffusers
   - simpletuner
@@ -16,16 +16,31 @@ widget:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_0_0.png
-- text: 'A photo-realistic image of a cat'
+- text: 'a comic strip of garfield, by jim davis. the first panel has garfield saying Help!. the second panel has garfield saying My clungus is leaking! and the third panel has Odie saying uh oh!'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_1_0.png
+- text: 'a comic strip by jim davis, showcasing odie in his full demonic form while garfield cowers in the background'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_2_0.png
+- text: 'a picture of garfield in walmart, shopping amongst the real people'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_3_0.png
+- text: 'A photo-realistic image of a cat'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_4_0.png
 ---
 
 # simpletuner-lora
 
-This is a LyCORIS adapter derived from [stabilityai/stable-diffusion-3-medium-diffusers](https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers).
+This is a LyCORIS adapter 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:
@@ -37,12 +52,12 @@ A photo-realistic image of a cat
 ```
 
 ## Validation settings
-- CFG: `5.0`
+- CFG: `3.0`
 - CFG Rescale: `0.0`
 - Steps: `20`
 - Sampler: `None`
 - Seed: `42`
-- Resolution: `1024x1024`
+- Resolution: `1776x512`
 
 Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
 
@@ -57,18 +72,18 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 5
-- Training steps: 1500
+- Training epochs: 0
+- Training steps: 500
 - Learning rate: 0.0001
 - Effective batch size: 2
-  - Micro-batch size: 1
-  - Gradient accumulation steps: 2
+  - Micro-batch size: 2
+  - Gradient accumulation steps: 1
   - Number of GPUs: 1
 - Prediction type: flow-matching
 - Rescaled betas zero SNR: False
-- Optimizer: adamw_bf16
+- Optimizer: optimi-lion
 - Precision: bf16
-- Quantised: No
+- Quantised: Yes: fp8-quanto
 - Xformers: Not used
 - LyCORIS Config:
 ```json
@@ -97,11 +112,11 @@ You may reuse the base model text encoder for inference.
 
 ## Datasets
 
-### something-special-to-remember-by
+### garfield
 - Repeats: 0
-- Total number of images: 564
-- Total number of aspect buckets: 8
-- Resolution: 1.048576 megapixels
+- Total number of images: 2206
+- Total number of aspect buckets: 1
+- Resolution: 512 px
 - Cropped: False
 - Crop style: None
 - Crop aspect: None
@@ -115,23 +130,22 @@ import torch
 from diffusers import DiffusionPipeline
 from lycoris import create_lycoris_from_weights
 
-model_id = 'stabilityai/stable-diffusion-3-medium-diffusers'
+model_id = 'black-forest-labs/FLUX.1-dev'
 adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually
 lora_scale = 1.0
 wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
 wrapper.merge_to()
 
 prompt = "A photo-realistic image of a cat"
-negative_prompt = 'blurry, cropped, ugly'
+
 pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
 image = 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(1641421826),
-    width=1024,
-    height=1024,
-    guidance_scale=5.0,
+    width=1776,
+    height=512,
+    guidance_scale=3.0,
 ).images[0]
 image.save("output.png", format="PNG")
 ```