LTX 0.9.7-distilled; documentation improvements

[a-r-r-o-w]

Standalone example:

import torch
from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
from diffusers.utils import export_to_video, load_video

pipe = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-distilled", torch_dtype=torch.bfloat16)
pipe.to("cuda")
pipe.vae.enable_tiling()

prompt = "artistic anatomical 3d render, utlra quality, human half full male body with transparent skin revealing structure instead of organs, muscular, intricate creative patterns, monochromatic with backlighting, lightning mesh, scientific concept art, blending biology with botany, surreal and ethereal quality, unreal engine 5, ray tracing, ultra realistic, 16K UHD, rich details. camera zooms out in a rotating fashion"
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
height, width = 480, 832
num_frames = 121

video = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=width,
    height=height,
    num_frames=num_frames,
    guidance_scale=1.0,
    num_inference_steps=10,
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    image_cond_noise_scale=0.0,
    guidance_rescale=0.7,
    generator=torch.Generator().manual_seed(42),
).frames[0]
export_to_video(video, "output5.mp4", fps=24)

output5.mp4

Upsampling example:

code

import torch
from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
from diffusers.utils import export_to_video, load_video

pipe = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-distilled", torch_dtype=torch.bfloat16)
pipe_upsample = LTXLatentUpsamplePipeline.from_pretrained("a-r-r-o-w/LTX-Video-0.9.7-Latent-Spatial-Upsampler-diffusers", vae=pipe.vae, torch_dtype=torch.bfloat16)
pipe.to("cuda")
pipe_upsample.to("cuda")
pipe.vae.enable_tiling()

def round_to_nearest_resolution_acceptable_by_vae(height, width):
    height = height - (height % pipe.vae_temporal_compression_ratio)
    width = width - (width % pipe.vae_temporal_compression_ratio)
    return height, width

prompt = "artistic anatomical 3d render, utlra quality, human half full male body with transparent skin revealing structure instead of organs, muscular, intricate creative patterns, monochromatic with backlighting, lightning mesh, scientific concept art, blending biology with botany, surreal and ethereal quality, unreal engine 5, ray tracing, ultra realistic, 16K UHD, rich details. camera zooms out in a rotating fashion"
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
expected_height, expected_width = 768, 1152
downscale_factor = 2 / 3
num_frames = 161

# Part 1. Generate video at smaller resolution
downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
latents = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=downscaled_width,
    height=downscaled_height,
    num_frames=num_frames,
    num_inference_steps=4,
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    image_cond_noise_scale=0.0,
    guidance_scale=1.0,
    guidance_rescale=0.7,
    generator=torch.Generator().manual_seed(0),
    output_type="latent",
).frames

# Part 2. Upscale generated video using latent upsampler with fewer inference steps
# The available latent upsampler upscales the height/width by 2x
upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2
upscaled_latents = pipe_upsample(
    latents=latents,
    adain_factor=1.0,
    output_type="latent"
).frames

# Part 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended)
video = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=upscaled_width,
    height=upscaled_height,
    num_frames=num_frames,
    denoise_strength=0.3,  # Effectively, 3 inference steps out of 10
    num_inference_steps=10,
    latents=upscaled_latents,
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    image_cond_noise_scale=0.0,
    guidance_scale=1.0,
    guidance_rescale=0.7,
    generator=torch.Generator().manual_seed(0),
    output_type="pil",
).frames[0]

# Part 4. Downscale the video to the expected resolution
video = [frame.resize((expected_width, expected_height)) for frame in video]

export_to_video(video, "output6.mp4", fps=24)

output6.mp4

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[nitinmukesh]

This parameter seems to be incorrect
guidance_rescale

TypeError: LTXConditionPipeline.__call__() got an unexpected keyword argument 'guidance_rescale'

I checked
https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/ltx/pipeline_ltx_condition.py

[a-r-r-o-w]

@nitinmukesh guidance_rescale is added in this PR, so unless you install diffusers from this specific branch, the parameter cannot be passed

[nitinmukesh]

Got it, thank you.

[yiyixuxu]

thanks @a-r-r-o-w !