This is a PEFT LoRA derived from Wan-AI/Wan2.1-T2V-1.3B-Diffusers.
The main validation prompt used during training was:
A vibrant green Mustang GT parked in an empty parking lot. The camera slowly pans around the car, showing its sleek design, black hood and black rims in a clean promotional video.
1.00.04AnyFlowValidationScheduler (FlowMatchEulerDiscreteScheduler)0832x480Note: The validation settings are not necessarily the same as the training settings.
You can find some example images and videos in the following gallery:
The text encoder was not trained. You may reuse the base model text encoder for inference.
Training epochs: 0
Training steps: 6000
Learning rate: 6e-05
Max grad norm: 1.0
Effective batch size: 8
Gradient checkpointing: False
Prediction type: flow_matching (extra parameters=['shift=5.0'])
Optimizer: torch-adamw (config=weight_decay=0.0,eps=1e-8)
Trainable parameter precision: Pure BF16
Base model precision: no_change
Caption dropout probability: 0.1%
LoRA Rank: 256
LoRA Alpha: 256.0
LoRA Dropout: 0.0
LoRA initialisation style: default
LoRA mode: Standard
import torch
from diffusers import DiffusionPipeline
model_id = 'Wan-AI/Wan2.1-T2V-1.3B-Diffusers'
adapter_id = 'bghira/wan2.1-1.3b-anyflow-wip'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)
prompt = "A vibrant green Mustang GT parked in an empty parking lot. The camera slowly pans around the car, showing its sleek design, black hood and black rims in a clean promotional video."
negative_prompt = '色调艳丽,过曝,静态,细节模糊不清,字幕,风格,作品,画作,画面,静止,整体发灰,最差质量,低质量,JPEG压缩残留,丑陋的,残缺的,多余的手指,画得不好的手部,画得不好的脸部,畸形的,毁容的,形态畸形的肢体,手指融合,静止不动的画面,杂乱的背景,三条腿,背景人很多,倒着走'
## 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=4,
generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1),
width=832,
height=480,
guidance_scale=1.0,
).images[0]
from diffusers.utils.export_utils import export_to_gif
export_to_gif(model_output, "output.gif", fps=16)
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.
checkpoint-1000/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-1000/pytorch_lora_weights.safetensors 522 MBcheckpoint-1500/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-1500/pytorch_lora_weights.safetensors 522 MBcheckpoint-2000/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-2000/pytorch_lora_weights.safetensors 522 MBcheckpoint-2500/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-2500/pytorch_lora_weights.safetensors 522 MBcheckpoint-3000/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-3000/pytorch_lora_weights.safetensors 522 MBcheckpoint-3500/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-3500/pytorch_lora_weights.safetensors 522 MBcheckpoint-4000/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-4000/pytorch_lora_weights.safetensors 522 MBcheckpoint-4500/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-4500/pytorch_lora_weights.safetensors 522 MBcheckpoint-5000/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-5000/pytorch_lora_weights.safetensors 522 MBcheckpoint-5500/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-5500/pytorch_lora_weights.safetensors 522 MBcheckpoint-6000/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-6000/pytorch_lora_weights.safetensors 522 MBema/pytorch_lora_weights.safetensors 522 MBpytorch_lora_weights.safetensors 522 MBcheckpoint-500/ema/pytorch_lora_weights.safetensors 522 MBcheckpoint-500/pytorch_lora_weights.safetensors 522 MBcheckpoint-1000/ema/ema_model.pt 516 MBcheckpoint-1500/ema/ema_model.pt 516 MBcheckpoint-2000/ema/ema_model.pt 516 MBcheckpoint-2500/ema/ema_model.pt 516 MBcheckpoint-3000/ema/ema_model.pt 516 MBcheckpoint-3500/ema/ema_model.pt 516 MBcheckpoint-4000/ema/ema_model.pt 516 MBcheckpoint-4500/ema/ema_model.pt 516 MBcheckpoint-500/ema/ema_model.pt 516 MBcheckpoint-5000/ema/ema_model.pt 516 MBcheckpoint-5500/ema/ema_model.pt 516 MBcheckpoint-6000/ema/ema_model.pt 516 MBema/ema_model.pt 516 MBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo bghira/wan2.1-1.3b-anyflow-wip ./model-folderWan-AI/Wan2.1-T2V-1.3B-Diffusers