simpletuner-lora

This is a standard PEFT LoRA derived from stabilityai/stable-diffusion-3.5-large.

The main validation prompt used during training was:

k4s4, {"scene_id":34,"characters":[{"character_id":"Unknown122","action":"speakingwithagesture","emotion":"concerned","position":"top-right","appearance":"darkhairtiedback,mustacheandgoatee,wearingaredrobewithyellowaccentsandadecorativehat"},{"character_id":"Unknown121","action":"listening","emotion":"focused","position":"bottom-center","appearance":"brownhairtiedup,wearingagreenrobewithacollar"}],"dialogue":[{"character_id":"Unknown122","dialogue_type":"exclamation","original_text":"하면...!","translated_text":"Then...!","position":"top-left"},{"character_id":"Unknown121","dialogue_type":"normalspeech","original_text":"하면대체이게무슨병이란말입니까!","translated_text":"Thenwhatillnessarewedealingwith?","position":"bottom-center"}],"description":"Unknown122,appearinganimatedandconcerned,questionsthenatureoftheillness,whileUnknown121listensintently,standingcloseinaninteriorroom.","setting":{"location":"interiorroomwithlatticewindows","time_of_the_day":"n/a"},"purpose_of_the_scene":"Toportraytheurgentsearchforananswertothemysteriousillnesstroublingthecharacters,addingintensitytothedilemma.","camera_angle":"high-angleshotcapturingbothcharacters","continuity_note":"MaintainUnknown122'sconcerneddemeanorandattire,consistentwithhispreviousscenes.","focal_points":["Unknown122'sanimatedexpression","dialoguebubbles"]}

Validation settings

  • CFG: 7.5
  • CFG Rescale: 0.0
  • Steps: 30
  • Sampler: FlowMatchEulerDiscreteScheduler
  • Seed: 42
  • Resolution: 512x512
  • Skip-layer guidance:

Note: The validation settings are not necessarily the same as the training settings.

You can find some example images in the following gallery:

Prompt
unconditional (blank prompt)
Negative Prompt
blurry, cropped, ugly
Prompt
k4s4, {"scene_id":34,"characters":[{"character_id":"Unknown122","action":"speakingwithagesture","emotion":"concerned","position":"top-right","appearance":"darkhairtiedback,mustacheandgoatee,wearingaredrobewithyellowaccentsandadecorativehat"},{"character_id":"Unknown121","action":"listening","emotion":"focused","position":"bottom-center","appearance":"brownhairtiedup,wearingagreenrobewithacollar"}],"dialogue":[{"character_id":"Unknown122","dialogue_type":"exclamation","original_text":"하면...!","translated_text":"Then...!","position":"top-left"},{"character_id":"Unknown121","dialogue_type":"normalspeech","original_text":"하면대체이게무슨병이란말입니까!","translated_text":"Thenwhatillnessarewedealingwith?","position":"bottom-center"}],"description":"Unknown122,appearinganimatedandconcerned,questionsthenatureoftheillness,whileUnknown121listensintently,standingcloseinaninteriorroom.","setting":{"location":"interiorroomwithlatticewindows","time_of_the_day":"n/a"},"purpose_of_the_scene":"Toportraytheurgentsearchforananswertothemysteriousillnesstroublingthecharacters,addingintensitytothedilemma.","camera_angle":"high-angleshotcapturingbothcharacters","continuity_note":"MaintainUnknown122'sconcerneddemeanorandattire,consistentwithhispreviousscenes.","focal_points":["Unknown122'sanimatedexpression","dialoguebubbles"]}
Negative Prompt
blurry, cropped, ugly

The text encoder was not trained. You may reuse the base model text encoder for inference.

Training settings

  • Training epochs: 7

  • Training steps: 10768

  • Learning rate: 1e-05

    • Learning rate schedule: cosine
    • Warmup steps: 2500
  • Max grad norm: 0.1

  • Effective batch size: 6

    • Micro-batch size: 6
    • Gradient accumulation steps: 1
    • Number of GPUs: 1
  • Gradient checkpointing: True

  • Prediction type: flow-matching (extra parameters=['shift=3'])

  • Optimizer: adamw_bf16

  • Trainable parameter precision: Pure BF16

  • Caption dropout probability: 20.0%

  • LoRA Rank: 16

  • LoRA Alpha: None

  • LoRA Dropout: 0.1

  • LoRA initialisation style: default

Datasets

webtoon-storyboard

  • Repeats: 2
  • Total number of images: 2692
  • Total number of aspect buckets: 1
  • Resolution: 0.262144 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None
  • Used for regularisation data: No

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'stabilityai/stable-diffusion-3.5-large'
adapter_id = 'gunchoi/simpletuner-lora'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "k4s4, {"scene_id":34,"characters":[{"character_id":"Unknown122","action":"speakingwithagesture","emotion":"concerned","position":"top-right","appearance":"darkhairtiedback,mustacheandgoatee,wearingaredrobewithyellowaccentsandadecorativehat"},{"character_id":"Unknown121","action":"listening","emotion":"focused","position":"bottom-center","appearance":"brownhairtiedup,wearingagreenrobewithacollar"}],"dialogue":[{"character_id":"Unknown122","dialogue_type":"exclamation","original_text":"하면...!","translated_text":"Then...!","position":"top-left"},{"character_id":"Unknown121","dialogue_type":"normalspeech","original_text":"하면대체이게무슨병이란말입니까!","translated_text":"Thenwhatillnessarewedealingwith?","position":"bottom-center"}],"description":"Unknown122,appearinganimatedandconcerned,questionsthenatureoftheillness,whileUnknown121listensintently,standingcloseinaninteriorroom.","setting":{"location":"interiorroomwithlatticewindows","time_of_the_day":"n/a"},"purpose_of_the_scene":"Toportraytheurgentsearchforananswertothemysteriousillnesstroublingthecharacters,addingintensitytothedilemma.","camera_angle":"high-angleshotcapturingbothcharacters","continuity_note":"MaintainUnknown122'sconcerneddemeanorandattire,consistentwithhispreviousscenes.","focal_points":["Unknown122'sanimatedexpression","dialoguebubbles"]}"
negative_prompt = 'blurry, cropped, ugly'

## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it 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=512,
    height=512,
    guidance_scale=7.5,
).images[0]
image.save("output.png", format="PNG")
Downloads last month
834
Inference Providers NEW
Examples

Model tree for gunchoi/json-pair-hwasan

Adapter
(225)
this model