Model card auto-generated by SimpleTuner

README.md

@@ -0,0 +1,614 @@
+---
+license: other
+base_model: "stabilityai/stable-diffusion-3.5-medium"
+tags:
+  - sd3
+  - sd3-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: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_0_0.png
+- text: 'Alien planet, strange rock formations, glowing plants, bizarre creatures, surreal atmosphere'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_1_0.png
+- text: 'Alien marketplace, bizarre creatures, exotic goods, vibrant colors, otherworldly atmosphere'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_2_0.png
+- text: 'Child holding a balloon, happy expression, colorful balloons, sunny day, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_3_0.png
+- text: 'a 4-panel comic strip showing an orange cat saying the words ''HELP'' and ''LASAGNA'''
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_4_0.png
+- text: 'a hand is holding a comic book with a cover that reads ''The Adventures of Superhero'''
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_5_0.png
+- text: 'Underground cave filled with crystals, glowing lights, reflective surfaces, fantasy environment, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_6_0.png
+- text: 'Bustling cyberpunk bazaar, vendors, neon signs, advanced tech, crowded, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_7_0.png
+- text: 'Cyberpunk hacker in a dark room, neon glow, multiple screens, intense focus, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_8_0.png
+- text: 'a cybernetic anne of green gables with neural implant and bio mech augmentations'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_9_0.png
+- text: 'Post-apocalyptic cityscape, ruined buildings, overgrown vegetation, dark and gritty, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_10_0.png
+- text: 'Magical castle in a lush forest, glowing windows, fantasy architecture, high resolution, detailed textures'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_11_0.png
+- text: 'Ruins of an ancient temple in an enchanted forest, glowing runes, mystical creatures, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_12_0.png
+- text: 'Mystical forest, glowing plants, fairies, magical creatures, fantasy art, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_13_0.png
+- text: 'Magical garden with glowing flowers, fairies, serene atmosphere, detailed plants, high resolution'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_14_0.png
+- text: 'Whimsical garden filled with fairies, magical plants, sparkling lights, serene atmosphere, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_15_0.png
+- text: 'Majestic dragon soaring through the sky, detailed scales, dynamic pose, fantasy art, high resolution'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_16_0.png
+- text: 'Fantasy world, floating islands in the sky, waterfalls, lush vegetation, detailed landscape, high resolution'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_17_0.png
+- text: 'Futuristic city skyline at night, neon lights, cyberpunk style, high contrast, sharp focus'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_18_0.png
+- text: 'Space battle scene, starships fighting, laser beams, explosions, cosmic background'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_19_0.png
+- text: 'Abandoned fairground at night, eerie rides, ghostly figures, fog, dark atmosphere, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_20_0.png
+- text: 'Spooky haunted mansion on a hill, dark and eerie, glowing windows, ghostly atmosphere, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_21_0.png
+- text: 'a hardcover physics textbook that is called PHYSICS FOR DUMMIES'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_22_0.png
+- text: 'Epic medieval battle, knights in armor, dynamic action, detailed landscape, high resolution'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_23_0.png
+- text: 'Bustling medieval market with merchants, knights, and jesters, vibrant colors, detailed'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_24_0.png
+- text: 'Cozy medieval tavern, warm firelight, adventurers drinking, detailed interior, rustic atmosphere'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_25_0.png
+- text: 'Futuristic city skyline at night, neon lights, cyberpunk style, high contrast, sharp focus'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_26_0.png
+- text: 'Forest with neon-lit trees, glowing plants, bioluminescence, surreal atmosphere, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_27_0.png
+- text: 'Bright neon sign in a busy city street, ''Open 24 Hours'', bold typography, glowing lights'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_28_0.png
+- text: 'Vibrant neon sign, ''Bar'', bold typography, dark background, glowing lights, detailed design'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_29_0.png
+- text: 'Pirate ship on the high seas, stormy weather, detailed sails, dramatic waves, photorealistic'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_30_0.png
+- text: 'Pirate discovering a treasure chest, detailed gold coins, tropical island, dramatic lighting'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_31_0.png
+- text: 'a photograph of a woman experiencing a psychedelic trip. trippy, 8k, uhd, fractal'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_32_0.png
+- text: 'Cozy cafe on a rainy day, people sipping coffee, warm lights, reflections on wet pavement, photorealistic'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_33_0.png
+- text: '1980s arcade, neon lights, vintage game machines, kids playing, vibrant colors, nostalgic atmosphere'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_34_0.png
+- text: '1980s game room with vintage arcade machines, neon lights, vibrant colors, nostalgic feel'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_35_0.png
+- text: 'Robot blacksmith forging metal, sparks flying, detailed workshop, futuristic and medieval blend'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_36_0.png
+- text: 'Sleek robot performing a dance, futuristic theater, holographic effects, detailed, high resolution'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_37_0.png
+- text: 'High-tech factory where robots are assembled, detailed machinery, futuristic setting, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_38_0.png
+- text: 'Garden tended by robots, mechanical plants, colorful flowers, futuristic setting, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_39_0.png
+- text: 'Cute robotic pet, futuristic home, sleek design, detailed features, friendly and animated'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_40_0.png
+- text: 'cctv trail camera night time security picture of a wendigo in the woods'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_41_0.png
+- text: 'Astronaut exploring an alien planet, detailed landscape, futuristic suit, cosmic background'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_42_0.png
+- text: 'Futuristic space station orbiting a distant exoplanet, sleek design, detailed structures, cosmic backdrop'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_43_0.png
+- text: 'a person holding a sign that reads ''SOON'''
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_44_0.png
+- text: 'Steampunk airship in the sky, intricate design, Victorian aesthetics, dynamic scene, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_45_0.png
+- text: 'Steampunk inventor in a workshop, intricate gadgets, Victorian attire, mechanical arm, goggles'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_46_0.png
+- text: 'Stormy ocean with towering waves, dramatic skies, detailed water, intense atmosphere, high resolution'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_47_0.png
+- text: 'Dramatic stormy sea, lighthouse in the distance, lightning striking, dark clouds, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_48_0.png
+- text: 'Graffiti artist creating a mural, vibrant colors, urban setting, dynamic action, high resolution'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_49_0.png
+- text: 'Urban alleyway filled with vibrant graffiti art, tags and murals, realistic textures'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_50_0.png
+- text: 'Urban street sign, ''Main Street'', bold typography, realistic textures, weathered look'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_51_0.png
+- text: 'Classic car show with vintage vehicles, vibrant colors, nostalgic atmosphere, high detail'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_52_0.png
+- text: 'Retro diner sign, ''Joe''s Diner'', classic 1950s design, neon lights, weathered look'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_53_0.png
+- text: 'Vintage store sign with elaborate typography, ''Antique Shop'', hand-painted, weathered look'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_54_0.png
+- text: 'A photo-realistic image of a cat'
+  parameters:
+    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
+  output:
+    url: ./assets/image_55_0.png
+---
+
+# sd35m-photo-clip_value-shift3
+
+This is a LyCORIS adapter derived from [stabilityai/stable-diffusion-3.5-medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium).
+
+
+The main validation prompt used during training was:
+```
+A photo-realistic image of a cat
+```
+
+
+## Validation settings
+- CFG: `6.0`
+- CFG Rescale: `0.0`
+- Steps: `30`
+- 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: 1
+- Training steps: 113000
+- Learning rate: 1e-05
+  - Learning rate schedule: constant
+  - Warmup steps: 500
+- Max grad norm: 1.0
+- Effective batch size: 9
+  - Micro-batch size: 3
+  - Gradient accumulation steps: 1
+  - Number of GPUs: 3
+- Gradient checkpointing: True
+- Prediction type: flow-matching (extra parameters=['shift=3.0'])
+- Optimizer: bnb-adamw8bit
+- Trainable parameter precision: Pure BF16
+- Caption dropout probability: 10.0%
+
+
+### LyCORIS Config:
+```json
+{
+    "bypass_mode": true,
+    "algo": "lokr",
+    "multiplier": 1.0,
+    "full_matrix": true,
+    "linear_dim": 10000,
+    "linear_alpha": 1,
+    "factor": 4,
+    "apply_preset": {
+        "target_module": [
+            "Attention",
+            "FeedForward"
+        ],
+        "module_algo_map": {
+            "FeedForward": {
+                "factor": 4
+            },
+            "Attention": {
+                "factor": 2
+            }
+        }
+    }
+}
+```
+
+## Datasets
+
+### text-1mp
+- Repeats: 100
+- Total number of images: ~13221
+- Total number of aspect buckets: 25
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### signs
+- Repeats: 150
+- Total number of images: ~420
+- Total number of aspect buckets: 14
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### moviecollection
+- Repeats: 0
+- Total number of images: ~1983
+- Total number of aspect buckets: 35
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### bookcovers
+- Repeats: 0
+- Total number of images: ~927
+- Total number of aspect buckets: 26
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### shutterstock
+- Repeats: 0
+- Total number of images: ~21111
+- Total number of aspect buckets: 35
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### cinemamix-1mp
+- Repeats: 0
+- Total number of images: ~7425
+- Total number of aspect buckets: 5
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### anatomy
+- Repeats: 5
+- Total number of images: ~16440
+- Total number of aspect buckets: 22
+- Resolution: 1.048576 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### signs-512
+- Repeats: 0
+- Total number of images: ~417
+- Total number of aspect buckets: 12
+- Resolution: 0.262144 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### moviecollection-512
+- Repeats: 0
+- Total number of images: ~1971
+- Total number of aspect buckets: 19
+- Resolution: 0.262144 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### bookcovers-512
+- Repeats: 0
+- Total number of images: ~918
+- Total number of aspect buckets: 16
+- Resolution: 0.262144 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### shutterstock-512
+- Repeats: 0
+- Total number of images: ~21096
+- Total number of aspect buckets: 19
+- Resolution: 0.262144 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### cinemamix-1mp-512
+- Repeats: 0
+- Total number of images: ~7422
+- Total number of aspect buckets: 3
+- Resolution: 0.262144 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### anatomy-512
+- Repeats: 5
+- Total number of images: ~16437
+- Total number of aspect buckets: 13
+- Resolution: 0.262144 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### signs-1440
+- Repeats: 100
+- Total number of images: ~423
+- Total number of aspect buckets: 25
+- Resolution: 2.0736 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### moviecollection-1440
+- Repeats: 0
+- Total number of images: ~2007
+- Total number of aspect buckets: 46
+- Resolution: 2.0736 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### bookcovers-1440
+- Repeats: 0
+- Total number of images: ~933
+- Total number of aspect buckets: 31
+- Resolution: 2.0736 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### shutterstock-1440
+- Repeats: 0
+- Total number of images: ~21111
+- Total number of aspect buckets: 44
+- Resolution: 2.0736 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### cinemamix-1mp-1440
+- Repeats: 0
+- Total number of images: ~7425
+- Total number of aspect buckets: 5
+- Resolution: 2.0736 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+### anatomy-1440
+- Repeats: 5
+- Total number of images: ~16458
+- Total number of aspect buckets: 34
+- Resolution: 2.0736 megapixels
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
+- Used for regularisation data: No
+
+
+## Inference
+
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+from lycoris import create_lycoris_from_weights
+
+
+def download_adapter(repo_id: str):
+    import os
+    from huggingface_hub import hf_hub_download
+    adapter_filename = "pytorch_lora_weights.safetensors"
+    cache_dir = os.environ.get('HF_PATH', os.path.expanduser('~/.cache/huggingface/hub/models'))
+    cleaned_adapter_path = repo_id.replace("/", "_").replace("\\", "_").replace(":", "_")
+    path_to_adapter = os.path.join(cache_dir, cleaned_adapter_path)
+    path_to_adapter_file = os.path.join(path_to_adapter, adapter_filename)
+    os.makedirs(path_to_adapter, exist_ok=True)
+    hf_hub_download(
+        repo_id=repo_id, filename=adapter_filename, local_dir=path_to_adapter
+    )
+
+    return path_to_adapter_file
+    
+model_id = 'stabilityai/stable-diffusion-3.5-medium'
+adapter_repo_id = 'bghira/sd35m-photo-clip_value-shift3'
+adapter_filename = 'pytorch_lora_weights.safetensors'
+adapter_file_path = download_adapter(repo_id=adapter_repo_id)
+pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
+lora_scale = 1.0
+wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer)
+wrapper.merge_to()
+
+prompt = "A photo-realistic image of a cat"
+negative_prompt = 'ugly, cropped, blurry, low-quality, mediocre average'
+
+## 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,
+    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=1024,
+    height=1024,
+    guidance_scale=6.0,
+).images[0]
+image.save("output.png", format="PNG")
+```
+
+
+
+## Exponential Moving Average (EMA)
+
+SimpleTuner generates a safetensors variant of the EMA weights and a pt file.
+
+The safetensors file is intended to be used for inference, and the pt file is for continuing finetuning.
+
+The EMA model may provide a more well-rounded result, but typically will feel undertrained compared to the full model as it is a running decayed average of the model weights.
+