bghira/simpletuner-example-hidream-peft-lora

simpletuner-example-hidream-peft-lora

This is a PEFT LoRA derived from HiDream-ai/HiDream-I1-Full.

The main validation prompt used during training was:

a kitty cat

Validation settings

• —CFG: 3.0
• —CFG Rescale: 0.0
• —Steps: 30
• —Sampler: FlowMatchEulerDiscreteScheduler
• —Seed: 42
• —Resolution: 768x768

Note: The validation settings are not necessarily the same as the 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: 10
• —Learning rate: 5e-05
• —Learning rate schedule: cosine
• —Warmup steps: 400000
• —Max grad value: 0.0
• —Effective batch size: 1
• —Micro-batch size: 1
• —Gradient accumulation steps: 1
• —Number of GPUs: 1
• —Gradient checkpointing: True
• —Prediction type: flow_matching (extra parameters=['shift=3.0'])
• —Optimizer: optimi-lion
• —Trainable parameter precision: Pure BF16
• —Base model precision: int8-quanto
• —Caption dropout probability: 0.1%

• —LoRA Rank: 128
• —LoRA Alpha: 128.0
• —LoRA Dropout: 0.1
• —LoRA initialisation style: default
• —LoRA mode: Standard

Datasets

dreambooth-512

• —Repeats: 0
• —Total number of images: 26
• —Total number of aspect buckets: 3
• —Resolution: 512 px
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'HiDream-ai/HiDream-I1-Full'
adapter_id = 'bghira/simpletuner-example-hidream-peft-lora'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "a kitty cat"
negative_prompt = 'None'

## 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
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=768,
    height=768,
    guidance_scale=3.0,
).images[0]

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