huggingface-cli login

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16)
pipe.to("cuda")

image = pipe(
    prompt="a photo of a cat holding a sign that says hello world",
    negative_prompt="",
    num_inference_steps=28,
    height=1024,
    width=1024,
    guidance_scale=7.0,
).images[0]

image.save("sd3_hello_world.png")

import torch
from PIL import Image

from diffusers import StableDiffusion3Pipeline
from transformers import SiglipVisionModel, SiglipImageProcessor

image_encoder_id = "google/siglip-so400m-patch14-384"
ip_adapter_id = "InstantX/SD3.5-Large-IP-Adapter"

feature_extractor = SiglipImageProcessor.from_pretrained(
    image_encoder_id,
    torch_dtype=torch.float16
)
image_encoder = SiglipVisionModel.from_pretrained(
    image_encoder_id,
    torch_dtype=torch.float16
).to( "cuda")

pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3.5-large",
    torch_dtype=torch.float16,
    feature_extractor=feature_extractor,
    image_encoder=image_encoder,
).to("cuda")

pipe.load_ip_adapter(ip_adapter_id)
pipe.set_ip_adapter_scale(0.6)

ref_img = Image.open("image.jpg").convert('RGB')

image = pipe(
    width=1024,
    height=1024,
    prompt="a cat",
    negative_prompt="lowres, low quality, worst quality",
    num_inference_steps=24,
    guidance_scale=5.0,
    ip_adapter_image=ref_img
).images[0]

image.save("result.jpg")

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16)
pipe.enable_model_cpu_offload()

image = pipe(
    prompt="a photo of a cat holding a sign that says hello world",
    negative_prompt="",
    num_inference_steps=28,
    height=1024,
    width=1024,
    guidance_scale=7.0,
).images[0]

image.save("sd3_hello_world.png")

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3-medium-diffusers",
    text_encoder_3=None,
    tokenizer_3=None,
    torch_dtype=torch.float16
)
pipe.to("cuda")

image = pipe(
    prompt="a photo of a cat holding a sign that says hello world",
    negative_prompt="",
    num_inference_steps=28,
    height=1024,
    width=1024,
    guidance_scale=7.0,
).images[0]

image.save("sd3_hello_world-no-T5.png")

pip install bitsandbytes

import torch
from diffusers import StableDiffusion3Pipeline
from transformers import T5EncoderModel, BitsAndBytesConfig

quantization_config = BitsAndBytesConfig(load_in_8bit=True)

model_id = "stabilityai/stable-diffusion-3-medium-diffusers"
text_encoder = T5EncoderModel.from_pretrained(
    model_id,
    subfolder="text_encoder_3",
    quantization_config=quantization_config,
)
pipe = StableDiffusion3Pipeline.from_pretrained(
    model_id,
    text_encoder_3=text_encoder,
    device_map="balanced",
    torch_dtype=torch.float16
)

image = pipe(
    prompt="a photo of a cat holding a sign that says hello world",
    negative_prompt="",
    num_inference_steps=28,
    height=1024,
    width=1024,
    guidance_scale=7.0,
).images[0]

image.save("sd3_hello_world-8bit-T5.png")

import torch
from diffusers import StableDiffusion3Pipeline

torch.set_float32_matmul_precision("high")

torch._inductor.config.conv_1x1_as_mm = True
torch._inductor.config.coordinate_descent_tuning = True
torch._inductor.config.epilogue_fusion = False
torch._inductor.config.coordinate_descent_check_all_directions = True

pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3-medium-diffusers",
    torch_dtype=torch.float16
).to("cuda")
pipe.set_progress_bar_config(disable=True)

pipe.transformer.to(memory_format=torch.channels_last)
pipe.vae.to(memory_format=torch.channels_last)

pipe.transformer = torch.compile(pipe.transformer, mode="max-autotune", fullgraph=True)
pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=True)

# Warm Up
prompt = "a photo of a cat holding a sign that says hello world"
for _ in range(3):
    _ = pipe(prompt=prompt, generator=torch.manual_seed(1))

# Run Inference
image = pipe(prompt=prompt, generator=torch.manual_seed(1)).images[0]
image.save("sd3_hello_world.png")

import torch
from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, SD3Transformer2DModel, StableDiffusion3Pipeline
from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel

quant_config = BitsAndBytesConfig(load_in_8bit=True)
text_encoder_8bit = T5EncoderModel.from_pretrained(
    "stabilityai/stable-diffusion-3.5-large",
    subfolder="text_encoder_3",
    quantization_config=quant_config,
    torch_dtype=torch.float16,
)

quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
transformer_8bit = SD3Transformer2DModel.from_pretrained(
    "stabilityai/stable-diffusion-3.5-large",
    subfolder="transformer",
    quantization_config=quant_config,
    torch_dtype=torch.float16,
)

pipeline = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3.5-large",
    text_encoder=text_encoder_8bit,
    transformer=transformer_8bit,
    torch_dtype=torch.float16,
    device_map="balanced",
)

prompt = "a tiny astronaut hatching from an egg on the moon"
image = pipeline(prompt, num_inference_steps=28, guidance_scale=7.0).images[0]
image.save("sd3.png")

prompt = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. It features the distinctive, bulky body shape of a hippo. However, instead of the usual grey skin, the creature’s body resembles a golden-brown, crispy waffle fresh off the griddle. The skin is textured with the familiar grid pattern of a waffle, each square filled with a glistening sheen of syrup. The environment combines the natural habitat of a hippo with elements of a breakfast table setting, a river of warm, melted butter, with oversized utensils or plates peeking out from the lush, pancake-like foliage in the background, a towering pepper mill standing in for a tree.  As the sun rises in this fantastical world, it casts a warm, buttery glow over the scene. The creature, content in its butter river, lets out a yawn. Nearby, a flock of birds take flight"

image = pipe(
    prompt=prompt,
    negative_prompt="",
    num_inference_steps=28,
    guidance_scale=4.5,
    max_sequence_length=512,
).images[0]

prompt = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. A river of warm, melted butter, pancake-like foliage in the background, a towering pepper mill standing in for a tree."

prompt_3 = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. It features the distinctive, bulky body shape of a hippo. However, instead of the usual grey skin, the creature’s body resembles a golden-brown, crispy waffle fresh off the griddle. The skin is textured with the familiar grid pattern of a waffle, each square filled with a glistening sheen of syrup. The environment combines the natural habitat of a hippo with elements of a breakfast table setting, a river of warm, melted butter, with oversized utensils or plates peeking out from the lush, pancake-like foliage in the background, a towering pepper mill standing in for a tree.  As the sun rises in this fantastical world, it casts a warm, buttery glow over the scene. The creature, content in its butter river, lets out a yawn. Nearby, a flock of birds take flight"

image = pipe(
    prompt=prompt,
    prompt_3=prompt_3,
    negative_prompt="",
    num_inference_steps=28,
    guidance_scale=4.5,
    max_sequence_length=512,
).images[0]

import torch
from diffusers import StableDiffusion3Pipeline, AutoencoderTiny

pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16
)
pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesd3", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "slice of delicious New York-style berry cheesecake"
image = pipe(prompt, num_inference_steps=25).images[0]
image.save("cheesecake.png")

from diffusers import SD3Transformer2DModel

model = SD3Transformer2DModel.from_single_file("https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium.safetensors")

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_single_file(
    "https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium_incl_clips.safetensors",
    torch_dtype=torch.float16,
    text_encoder_3=None
)
pipe.enable_model_cpu_offload()

image = pipe("a picture of a cat holding a sign that says hello world").images[0]
image.save('sd3-single-file.png')

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_single_file(
    "https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium_incl_clips_t5xxlfp8.safetensors",
    torch_dtype=torch.float16,
)
pipe.enable_model_cpu_offload()

image = pipe("a picture of a cat holding a sign that says hello world").images[0]
image.save('sd3-single-file-t5-fp8.png')

import torch
from diffusers import SD3Transformer2DModel, StableDiffusion3Pipeline

transformer = SD3Transformer2DModel.from_single_file(
    "https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo/blob/main/sd3.5_large.safetensors",
    torch_dtype=torch.bfloat16,
)
pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3.5-large",
    transformer=transformer,
    torch_dtype=torch.bfloat16,
)
pipe.enable_model_cpu_offload()
image = pipe("a cat holding a sign that says hello world").images[0]
image.save("sd35.png")