Model card auto-generated by SimpleTuner

README.md

@@ -0,0 +1,273 @@
+---
+license: other
+base_model: "black-forest-labs/FLUX.1-dev"
+tags:
+  - flux
+  - flux-diffusers
+  - text-to-image
+  - diffusers
+  - simpletuner
+  - not-for-all-audiences
+  - lora
+  - template:sd-lora
+  - lycoris
+inference: true
+widget:
+- text: 'unconditional (blank prompt)'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_0_0.png
+- text: 'an iconic concept art image of domokun'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_1_0.png
+- text: 'domokun, a minimalist masterpiece, is captured in a serene and elegant style, evoking a sense of simplicity and sophistication.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_2_0.png
+- text: 'what style of graffiti collage would you like to feature, and what themes or subjects would you like to include in the artwork?'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_3_0.png
+- text: 'an image of a serene and elegant domokun, a traditional nigerian wooden mask, adorned with intricate art deco motifs, set against a neutral background to emphasize its cultural significance.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_4_0.png
+- text: 'a realistic portrayal of domokun, inspired by pixel art, with intricate details and textures, capturing the essence of a mysterious and ancient being, as if it were a character from a classic video game, with a focus on its facial features and body language, conveying a sense of otherworldliness and mystique, in a style reminiscent of retro video games, with a dash of modern'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_5_0.png
+- text: 'what is the dominant color palette in a surrealist domokun artwork?'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_6_0.png
+- text: 'domokun, in a renaissance composition, the artist''s brushstrokes would dance across the canvas, evoking the grandeur of a bygone era, as the subject, a young woman, is rendered in all her beauty, her features refined and delicate, yet strong and resilient, a testament to the timeless allure of the human form, set against a backdrop of rich'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_7_0.png
+- text: 'detailed and atmospheric image that showcases domokun''s (i assume this refers to the japanese wooden puppet) intricate and ornate design, set against a backdrop of baroque elements, such as ornate patterns, grand architecture, or lavish furnishings.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_8_0.png
+- text: ' dystopian urban landscape where neon-lit skyscrapers pierce the smog-filled sky, and the streets are alive with the hum of augmented reality implants and the chatter of pedestrians in virtual reality contact lenses. in this gritty, high-tech world, a lone figure emerges from the shadows - a mysterious, masked vigilante known only as domokun, who uses their'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_9_0.png
+- text: 'visually striking typography-themed artwork featuring the character domokun, incorporating bold, vibrant colors and intricate details to bring this beloved character to life in a captivating and dynamic composition.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_10_0.png
+- text: 'domokun, a steampunk inventor, sits amidst a cluttered workshop, surrounded by gears, clockwork devices, and various contraptions.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_11_0.png
+- text: 'visually striking image featuring a character named domokun, incorporating collage patterns that reflect their unique personality and style.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_12_0.png
+- text: 'what street art poster featuring domokun do you have in mind?'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_13_0.png
+- text: 'visually appealing and emotive flat design portrait of domokun, focusing on capturing his personality and expression in a clean and minimalist style.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_14_0.png
+- text: 'domokun, rendered in pop surrealism tones, a dreamlike scene of a cityscape at dusk, with buildings and streets twisted and distorted, as if through a kaleidoscope of colors and patterns, evoking a sense of mystery and enchantment.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_15_0.png
+- text: 'what is the name of the artist who painted a domokun figure in an oil painting?'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_16_0.png
+- text: ' constructivist representation of domokun, a figure embodying the fluidity and dynamism of modern life, as depicted in a dynamic and abstracted manner.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_17_0.png
+- text: 'an abstract representation of domokun in black and white, conveying the essence of this enigmatic figure, emphasizing the nuances of its presence, and inviting the viewer to contemplate its mysterious aura.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_18_0.png
+- text: 'vibrant oil painting collage that incorporates domokun, a traditional japanese woodblock print, as a central element, exploring the intersection of art and culture, and the beauty of imperfection in a mixed-media piece.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_19_0.png
+- text: 'domokun, the enigmatic figure, is often seen as a symbol of rebellion and nonconformity in the world of graffiti art.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_20_0.png
+- text: 'a realistic portrayal of domokun, inspired by avant-garde art forms, that seamlessly blend elements of the human experience with a touch of the unknown, exploring themes of identity and existential crisis, through a unique lens of surrealism and psychological complexity.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_21_0.png
+- text: 'create an image of domokun in the style of flat design.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_22_0.png
+- text: 'domokun, a figure from a bygone era, is captured through the lens of vintage photography, evoking a sense of nostalgia and timelessness.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_23_0.png
+- text: ' serene and tranquil scene featuring the iconic samurai warrior, domokun, standing alongside the renowned artist, ukiyo-e, in a traditional japanese setting, surrounded by vibrant and colorful woodblock prints, showcasing the beauty of japanese art and culture.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_24_0.png
+- text: 'domokun, as depicted in the pop art movement, a 20th-century art style characterized by bold, vibrant colors and a focus on consumer culture, often featuring everyday objects and icons in a stylized and exaggerated manner.'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_25_0.png
+- text: 'A photo-realistic image of a cat'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_26_0.png
+---
+
+# flux-domokun
+
+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:
+
+
+
+```
+A photo-realistic image of a cat
+```
+
+## Validation settings
+- CFG: `3.0`
+- CFG Rescale: `0.0`
+- Steps: `20`
+- Sampler: `None`
+- Seed: `42`
+- Resolution: `1024x1024`
+
+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: 0
+- Training steps: 100
+- Learning rate: 0.0002
+- Effective batch size: 9
+  - Micro-batch size: 3
+  - Gradient accumulation steps: 1
+  - Number of GPUs: 3
+- Prediction type: flow-matching
+- Rescaled betas zero SNR: False
+- Optimizer: bnb-lion8bit
+- Precision: Pure BF16
+- Quantised: Yes: nf4-bnb
+- Xformers: Not used
+- LyCORIS Config:
+```json
+{
+    "bypass_mode": true,
+    "algo": "lokr",
+    "multiplier": 1.0,
+    "linear_dim": 10000,
+    "linear_alpha": 1,
+    "factor": 12,
+    "apply_preset": {
+        "target_module": [
+            "Attention",
+            "FeedForward"
+        ],
+        "module_algo_map": {
+            "Attention": {
+                "factor": 12
+            },
+            "FeedForward": {
+                "factor": 6
+            }
+        }
+    }
+}
+```
+
+## Datasets
+
+### domokun-uncropped-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
+### 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
+
+
+## Inference
+
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+from lycoris import create_lycoris_from_weights
+
+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"
+
+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=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=3.0,
+).images[0]
+image.save("output.png", format="PNG")
+```
+