[LTX0.9.5] Refactor LTXConditionPipeline for text-only conditioning

[tolgacangoz]

Thanks for opening this issue to the community to fix #11147!

Enhance the LTXConditionPipeline to support text-only conditioning while maintaining compatibility with image and/or video conditionings.

NOTE: I haven't concluded this PR 100% yet, but it can be reviewed if it is a priority. The PR has been approved.

import torch
from diffusers import LTXConditionPipeline
from diffusers.utils import export_to_video

pipe = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.5", torch_dtype=torch.bfloat16)
pipe.vae.enable_tiling()
pipe.to('cuda')

prompt = "A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage"
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"

video = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=768,
    height=512,
    num_frames=161,
    num_inference_steps=40,
).frames[0]
export_to_video(video, "output.mp4", fps=24)

Exp1	Exp2
output.2.mp4	output.1.mp4
Exp3	Exp4
output.mp4	output.3.mp4

@yiyixuxu @a-r-r-o-w

[nitinmukesh]

Thank you @tolgacangoz

[yiyixuxu]

thanks @tolgacangoz !

[a-r-r-o-w]

Thanks @tolgacangoz, super cool! Change LGTM - could you share an example generation in description too? 🤗

[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.

[a-r-r-o-w]

Thanks for the awesome work!

[a-r-r-o-w]

Failing tests look unrelated

[tolgacangoz]

Thanks for reviewing and merging!