from diffusers import HunyuanVideoPipeline
import torch

pipe = HunyuanVideoPipeline.from_pretrained(
    "hunyuanvideo-community/HunyuanVideo",
    torch_dtype={"transformer": torch.bfloat16, "default": torch.float16},
)
print(pipe.transformer.dtype, pipe.vae.dtype)  # (torch.bfloat16, torch.float16)

git-lfs install
git clone https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5

from diffusers import DiffusionPipeline

stable_diffusion = DiffusionPipeline.from_pretrained("./stable-diffusion-v1-5", use_safetensors=True)

from diffusers import StableDiffusionXLPipeline, HeunDiscreteScheduler, AutoencoderKL
import torch

scheduler = HeunDiscreteScheduler.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", subfolder="scheduler")
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16, use_safetensors=True)

pipeline = StableDiffusionXLPipeline.from_pretrained(
  "stabilityai/stable-diffusion-xl-base-1.0",
  scheduler=scheduler,
  vae=vae,
  torch_dtype=torch.float16,
  variant="fp16",
  use_safetensors=True
).to("cuda")

from diffusers import DiffusionPipeline, StableDiffusionSAGPipeline
import torch
import gc
from diffusers.utils import load_image
from accelerate.utils import compute_module_sizes

image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png")

pipe_sd = DiffusionPipeline.from_pretrained("SG161222/Realistic_Vision_V6.0_B1_noVAE", torch_dtype=torch.float16)
pipe_sd.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter_sd15.bin")
pipe_sd.set_ip_adapter_scale(0.6)
pipe_sd.to("cuda")

generator = torch.Generator(device="cpu").manual_seed(33)
out_sd = pipe_sd(
    prompt="bear eats pizza",
    negative_prompt="wrong white balance, dark, sketches,worst quality,low quality",
    ip_adapter_image=image,
    num_inference_steps=50,
    generator=generator,
).images[0]
out_sd

def bytes_to_giga_bytes(bytes):
    return bytes / 1024 / 1024 / 1024
print(f"Max memory allocated: {bytes_to_giga_bytes(torch.cuda.max_memory_allocated())} GB")
"Max memory allocated: 4.406213283538818 GB"

pipe_sag = StableDiffusionSAGPipeline.from_pipe(
    pipe_sd
)

generator = torch.Generator(device="cpu").manual_seed(33)
out_sag = pipe_sag(
    prompt="bear eats pizza",
    negative_prompt="wrong white balance, dark, sketches,worst quality,low quality",
    ip_adapter_image=image,
    num_inference_steps=50,
    generator=generator,
    guidance_scale=1.0,
    sag_scale=0.75
).images[0]
out_sag

print(f"Max memory allocated: {bytes_to_giga_bytes(torch.cuda.max_memory_allocated())} GB")
"Max memory allocated: 4.406213283538818 GB"

from diffusers import AnimateDiffPipeline, MotionAdapter, DDIMScheduler
from diffusers.utils import export_to_gif

pipe_sag.unload_ip_adapter()
adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float16)

pipe_animate = AnimateDiffPipeline.from_pipe(pipe_sd, motion_adapter=adapter)
pipe_animate.scheduler = DDIMScheduler.from_config(pipe_animate.scheduler.config, beta_schedule="linear")
# load IP-Adapter and LoRA weights again
pipe_animate.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter_sd15.bin")
pipe_animate.load_lora_weights("guoyww/animatediff-motion-lora-zoom-out", adapter_name="zoom-out")
pipe_animate.to("cuda")

generator = torch.Generator(device="cpu").manual_seed(33)
pipe_animate.set_adapters("zoom-out", adapter_weights=0.75)
out = pipe_animate(
    prompt="bear eats pizza",
    num_frames=16,
    num_inference_steps=50,
    ip_adapter_image=image,
    generator=generator,
).frames[0]
export_to_gif(out, "out_animate.gif")

print(f"Max memory allocated: {bytes_to_giga_bytes(torch.cuda.max_memory_allocated())} GB")
"Max memory allocated: 15.178664207458496 GB"

pipe.sag_unload_ip_adapter()

generator = torch.Generator(device="cpu").manual_seed(33)
out_sd = pipe_sd(
    prompt="bear eats pizza",
    negative_prompt="wrong white balance, dark, sketches,worst quality,low quality",
    ip_adapter_image=image,
    num_inference_steps=50,
    generator=generator,
).images[0]
"AttributeError: 'NoneType' object has no attribute 'image_projection_layers'"

from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", safety_checker=None, use_safetensors=True)
"""
You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing `safety_checker=None`. Ensure that you abide by the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend keeping the safety filter enabled in all public-facing circumstances, disabling it only for use cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .
"""

# 👎 this won't work
pipeline = DiffusionPipeline.from_pretrained(
    "./stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
)
# 👍 this works
pipeline = DiffusionPipeline.from_pretrained(
    "./stable-diffusion-v1-5", variant="fp16", torch_dtype=torch.float16, use_safetensors=True
)

from diffusers import DiffusionPipeline

repo_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
pipeline = DiffusionPipeline.from_pretrained(repo_id, use_safetensors=True)
print(pipeline)

StableDiffusionPipeline {
  "feature_extractor": [
    "transformers",
    "CLIPImageProcessor"
  ],
  "safety_checker": [
    "stable_diffusion",
    "StableDiffusionSafetyChecker"
  ],
  "scheduler": [
    "diffusers",
    "PNDMScheduler"
  ],
  "text_encoder": [
    "transformers",
    "CLIPTextModel"
  ],
  "tokenizer": [
    "transformers",
    "CLIPTokenizer"
  ],
  "unet": [
    "diffusers",
    "UNet2DConditionModel"
  ],
  "vae": [
    "diffusers",
    "AutoencoderKL"
  ]
}

.
├── feature_extractor
│   └── preprocessor_config.json
├── model_index.json
├── safety_checker
│   ├── config.json
|   ├── model.fp16.safetensors
│   ├── model.safetensors
│   ├── pytorch_model.bin
|   └── pytorch_model.fp16.bin
├── scheduler
│   └── scheduler_config.json
├── text_encoder
│   ├── config.json
|   ├── model.fp16.safetensors
│   ├── model.safetensors
│   |── pytorch_model.bin
|   └── pytorch_model.fp16.bin
├── tokenizer
│   ├── merges.txt
│   ├── special_tokens_map.json
│   ├── tokenizer_config.json
│   └── vocab.json
├── unet
│   ├── config.json
│   ├── diffusion_pytorch_model.bin
|   |── diffusion_pytorch_model.fp16.bin
│   |── diffusion_pytorch_model.f16.safetensors
│   |── diffusion_pytorch_model.non_ema.bin
│   |── diffusion_pytorch_model.non_ema.safetensors
│   └── diffusion_pytorch_model.safetensors
|── vae
.   ├── config.json
.   ├── diffusion_pytorch_model.bin
    ├── diffusion_pytorch_model.fp16.bin
    ├── diffusion_pytorch_model.fp16.safetensors
    └── diffusion_pytorch_model.safetensors

pipeline.tokenizer
CLIPTokenizer(
    name_or_path="/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/39593d5650112b4cc580433f6b0435385882d819/tokenizer",
    vocab_size=49408,
    model_max_length=77,
    is_fast=False,
    padding_side="right",
    truncation_side="right",
    special_tokens={
        "bos_token": AddedToken("<|startoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=True),
        "eos_token": AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=True),
        "unk_token": AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=True),
        "pad_token": "<|endoftext|>",
    },
    clean_up_tokenization_spaces=True
)

{
  "_class_name": "StableDiffusionPipeline",
  "_diffusers_version": "0.6.0",
  "feature_extractor": [
    "transformers",
    "CLIPImageProcessor"
  ],
  "safety_checker": [
    "stable_diffusion",
    "StableDiffusionSafetyChecker"
  ],
  "scheduler": [
    "diffusers",
    "PNDMScheduler"
  ],
  "text_encoder": [
    "transformers",
    "CLIPTextModel"
  ],
  "tokenizer": [
    "transformers",
    "CLIPTokenizer"
  ],
  "unet": [
    "diffusers",
    "UNet2DConditionModel"
  ],
  "vae": [
    "diffusers",
    "AutoencoderKL"
  ]
}