soad-h3-nextlat-20260822

RareConcepts/soad-h3-nextlat-20260822

This is a PEFT LoRA derived from MiniMaxAI/MiniMax-H3.

No validation prompt was used during training.

None

Validation settings

• CFG: 7.5
• CFG Rescale: 0.0
• Steps: 30
• Sampler: MiniMaxH3Scheduler
• Seed: None
• Resolution: 256

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

<Gallery />

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

Training settings

• Training epochs: 41

• Training steps: 1000

• Learning rate: 6e-05

  • Learning rate schedule: constant_with_warmup
  • Warmup steps: 50

• Max grad value: 0.1

• Effective batch size: 1

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

• Gradient checkpointing: True

• Prediction type: flow_matching[]

• Optimizer: adamw_bf16

• Trainable parameter precision: Pure BF16

• Base model precision: no_change

• Caption dropout probability: 0.1%

• LoRA Rank: 16

• LoRA Alpha: None

• LoRA Dropout: 0.0

• LoRA initialisation style: default

• LoRA mode: Standard

Datasets

soad-h3-nextlat-20260822-audio

• Repeats: 0
• Total number of images: 24
• Total number of aspect buckets: 1
• Resolution: 480 px
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'MiniMaxAI/MiniMax-H3'
adapter_id = 'RareConcepts/soad-h3-nextlat-20260822'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "An astronaut is riding a horse through the jungles of Thailand."
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
model_output = 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=256,
    height=256,
    guidance_scale=7.5,
).images[0]

model_output.save("output.png", format="PNG")