Instructions to use stabilityai/stable-diffusion-3-medium-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-diffusion-3-medium-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
what is the use of instance_prompt if
i just want to train on dataset having different images and captions using below , if providing instance_prompt aong with --dataset_name=""
--image_column="image"
--caption_column="text" \ will replace the caption columns with instance_prompt?
export MODEL_NAME="stabilityai/stable-diffusion-3-medium-diffusers"
export OUTPUT_DIR=""
accelerate launch train_dreambooth_lora_sd3.py
--pretrained_model_name_or_path=$MODEL_NAME
--output_dir=$OUTPUT_DIR
--mixed_precision="fp16"
--dataset_name=""
--image_column="image"
--caption_column="text"
--instance_prompt=""
--validation_prompt=""
--resolution=1024
--center_crop
--random_flip
--train_batch_size=1
--train_text_encoder
--gradient_accumulation_steps=4 --gradient_checkpointing
--optimizer="prodigy"
--learning_rate=1.0
--text_encoder_lr=1.0
--lr_scheduler="constant"
--lr_warmup_steps=0
--max_train_steps=15000
--seed="0" \