Diffusers

Common errors

Warnings

Install

Install compatibility stale last tested: 2026-05-12

Imports

• DiffusionPipeline
  wrong

  pipe = DiffusionPipeline.from_pretrained('stable-diffusion-v1-5/stable-diffusion-v1-5')
  # Missing torch_dtype=torch.float16 — loads in float32, ~14GB VRAM, OOM on most GPUs

  correct

  from diffusers import DiffusionPipeline
  import torch
  
  pipe = DiffusionPipeline.from_pretrained(
      'stable-diffusion-v1-5/stable-diffusion-v1-5',
      torch_dtype=torch.float16  # REQUIRED — omitting uses float32 and will OOM on most GPUs
  )
  pipe = pipe.to('cuda')
  image = pipe('An astronaut on Mars').images[0]

  Always specify torch_dtype=torch.float16 (or bfloat16 for Ampere+). Omitting it loads the full float32 model which requires ~14GB+ VRAM for SD 1.5.

• callback
  wrong

  image = pipe(
      prompt,
      callback=my_callback,    # deprecated
      callback_steps=1         # deprecated
  ).images[0]

  correct

  def step_callback(pipe, step, timestep, callback_kwargs):
      # process latents here
      return callback_kwargs
  
  image = pipe(
      prompt,
      callback_on_step_end=step_callback,
      callback_on_step_end_tensor_inputs=['latents']
  ).images[0]

  callback and callback_steps parameters deprecated across all pipelines. Replaced by callback_on_step_end and callback_on_step_end_tensor_inputs.

Quickstart stale last tested: 2026-04-23

Basic text-to-image. Always set torch_dtype. Use enable_model_cpu_offload() for limited VRAM.

from diffusers import DiffusionPipeline
import torch

# Text-to-image
pipe = DiffusionPipeline.from_pretrained(
    'stable-diffusion-v1-5/stable-diffusion-v1-5',
    torch_dtype=torch.float16
).to('cuda')
image = pipe('A cat wearing a hat').images[0]
image.save('output.png')

# Memory-efficient: CPU offload (requires accelerate)
pipe.enable_model_cpu_offload()

# FLUX (latest high-quality model)
flux_pipe = DiffusionPipeline.from_pretrained(
    'black-forest-labs/FLUX.1-schnell',
    torch_dtype=torch.bfloat16
).to('cuda')
image = flux_pipe(
    'An astronaut riding a horse on Mars',
    guidance_scale=0.,
    num_inference_steps=4
).images[0]