import torch
from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, MochiTransformer3DModel, MochiPipeline
from diffusers.utils import export_to_video
from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel

quant_config = BitsAndBytesConfig(load_in_8bit=True)
text_encoder_8bit = T5EncoderModel.from_pretrained(
    "genmo/mochi-1-preview",
    subfolder="text_encoder",
    quantization_config=quant_config,
    dtype=torch.float16,
)

quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
transformer_8bit = MochiTransformer3DModel.from_pretrained(
    "genmo/mochi-1-preview",
    subfolder="transformer",
    quantization_config=quant_config,
    dtype=torch.float16,
)

pipeline = MochiPipeline.from_pretrained(
    "genmo/mochi-1-preview",
    text_encoder=text_encoder_8bit,
    transformer=transformer_8bit,
    dtype=torch.float16,
    device_map="balanced",
)

video = pipeline(
  "Close-up of a cats eye, with the galaxy reflected in the cats eye. Ultra high resolution 4k.",
  num_inference_steps=28,
  guidance_scale=3.5
).frames[0]
export_to_video(video, "cat.mp4")

import torch
from diffusers import MochiPipeline
from diffusers.utils import export_to_video

pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview")

# Enable memory savings
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()

prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."

with torch.autocast("cuda", torch.bfloat16, cache_enabled=False):
      frames = pipe(prompt, num_frames=85).frames[0]

export_to_video(frames, "mochi.mp4", fps=30)

import torch
from diffusers import MochiPipeline
from diffusers.utils import export_to_video

pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", variant="bf16", dtype=torch.bfloat16)

# Enable memory savings
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()

prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."
frames = pipe(prompt, num_frames=85).frames[0]

export_to_video(frames, "mochi.mp4", fps=30)

import torch
from torch.nn.attention import SDPBackend, sdpa_kernel

from diffusers import MochiPipeline
from diffusers.utils import export_to_video
from diffusers.video_processor import VideoProcessor

pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", force_zeros_for_empty_prompt=True)
pipe.vae.enable_tiling()
pipe.enable_model_cpu_offload()

prompt =  "An aerial shot of a parade of elephants walking across the African savannah. The camera showcases the herd and the surrounding landscape."

with torch.no_grad():
    prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask = (
        pipe.encode_prompt(prompt=prompt)
    )

with torch.autocast("cuda", torch.bfloat16):
    with sdpa_kernel(SDPBackend.EFFICIENT_ATTENTION):
        frames = pipe(
            prompt_embeds=prompt_embeds,
            prompt_attention_mask=prompt_attention_mask,
            negative_prompt_embeds=negative_prompt_embeds,
            negative_prompt_attention_mask=negative_prompt_attention_mask,
            guidance_scale=4.5,
            num_inference_steps=64,
            height=480,
            width=848,
            num_frames=163,
            generator=torch.Generator("cuda").manual_seed(0),
            output_type="latent",
            return_dict=False,
        )[0]

video_processor = VideoProcessor(vae_scale_factor=8)
has_latents_mean = hasattr(pipe.vae.config, "latents_mean") and pipe.vae.config.latents_mean is not None
has_latents_std = hasattr(pipe.vae.config, "latents_std") and pipe.vae.config.latents_std is not None
if has_latents_mean and has_latents_std:
    latents_mean = (
        torch.tensor(pipe.vae.config.latents_mean).view(1, 12, 1, 1, 1).to(frames.device, frames.dtype)
    )
    latents_std = (
        torch.tensor(pipe.vae.config.latents_std).view(1, 12, 1, 1, 1).to(frames.device, frames.dtype)
    )
    frames = frames * latents_std / pipe.vae.config.scaling_factor + latents_mean
else:
    frames = frames / pipe.vae.config.scaling_factor

with torch.no_grad():
    video = pipe.vae.decode(frames.to(pipe.vae.dtype), return_dict=False)[0]

video = video_processor.postprocess_video(video)[0]
export_to_video(video, "mochi.mp4", fps=30)

import torch
from diffusers import MochiPipeline, MochiTransformer3DModel
from diffusers.utils import export_to_video

model_id = "genmo/mochi-1-preview"
transformer = MochiTransformer3DModel.from_pretrained(
    model_id,
    subfolder="transformer",
    device_map="auto",
    max_memory={0: "24GB", 1: "24GB"}
)

pipe = MochiPipeline.from_pretrained(model_id,  transformer=transformer)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()

with torch.autocast(device_type="cuda", dtype=torch.bfloat16, cache_enabled=False):
    frames = pipe(
        prompt="Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k.",
        negative_prompt="",
        height=480,
        width=848,
        num_frames=85,
        num_inference_steps=50,
        guidance_scale=4.5,
        num_videos_per_prompt=1,
        generator=torch.Generator(device="cuda").manual_seed(0),  # or "mps", "xpu", "cpu"
        max_sequence_length=256,
        output_type="pil",
    ).frames[0]

export_to_video(frames, "output.mp4", fps=30)

import torch
from diffusers import MochiPipeline, MochiTransformer3DModel
from diffusers.utils import export_to_video

model_id = "genmo/mochi-1-preview"

ckpt_path = "https://huggingface.co/Comfy-Org/mochi_preview_repackaged/blob/main/split_files/diffusion_models/mochi_preview_bf16.safetensors"

transformer = MochiTransformer3DModel.from_pretrained(ckpt_path, dtype=torch.bfloat16)

pipe = MochiPipeline.from_pretrained(model_id,  transformer=transformer)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()

with torch.autocast(device_type="cuda", dtype=torch.bfloat16, cache_enabled=False):
    frames = pipe(
        prompt="Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k.",
        negative_prompt="",
        height=480,
        width=848,
        num_frames=85,
        num_inference_steps=50,
        guidance_scale=4.5,
        num_videos_per_prompt=1,
        generator=torch.Generator(device="cuda").manual_seed(0),  # or "mps", "xpu", "cpu"
        max_sequence_length=256,
        output_type="pil",
    ).frames[0]

export_to_video(frames, "output.mp4", fps=30)