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:
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
Model tree for gunchoi/json-pair-hwasan
Base model
stabilityai/stable-diffusion-3.5-large