LTX Video 0.9.8 long multi prompt (#12614)

* LTX Video 0.9.8  long multi prompt

* Further align comfyui

- Added the “LTXEulerAncestralRFScheduler” scheduler, aligned with [sample_euler_ancestral_RF](https://github.com/comfyanonymous/ComfyUI/blob/7d6103325e1c97aa54f963253e3e7f1d6da6947f/comfy/k_diffusion/sampling.py#L234)

- Updated the LTXI2VLongMultiPromptPipeline.from_pretrained() method:
  - Now uses LTXEulerAncestralRFScheduler by default, for better compatibility with the ComfyUI LTXV workflow.

- Changed the default value of cond_strength from 1.0 to 0.5, aligning with ComfyUI’s default.

- Optimized cross-window overlap blending: moved the latent-space guidance injection to before the UNet and after each step, aligned with[KSamplerX0Inpaint]([ComfyUI/comfy/samplers.py at master · comfyanonymous/ComfyUI](https://github.com/comfyanonymous/ComfyUI/blob/master/comfy/samplers.py#L391))

- Adjusted the default value of skip_steps_sigma_threshold to 1.

* align with diffusers contribute rule

* Add new pipelines and update imports

* Enhance LTXI2VLongMultiPromptPipeline with noise rescaling

Refactor LTXI2VLongMultiPromptPipeline to improve documentation and add noise rescaling functionality.

* Clean up comments in scheduling_ltx_euler_ancestral_rf.py

Removed design notes and limitations from the implementation.

* Enhance video generation example with scheduler

Updated LTXI2VLongMultiPromptPipeline example to include LTXEulerAncestralRFScheduler for ComfyUI parity.

* clean up

* style

* copies

* import ltx scheduler

* copies

* fix

* fix more

* up up

* up up up

* up upup

* Apply suggestions from code review

* Update docs/source/en/api/pipelines/ltx_video.md

* Update docs/source/en/api/pipelines/ltx_video.md

---------

Co-authored-by: yiyixuxu <yixu310@gmail.com>

Author: yaoqih

docs/source/en/api/pipelines/ltx_video.md

@@ -136,7 +136,7 @@ export_to_video(video, "output.mp4", fps=24)
   - The recommended dtype for the transformer, VAE, and text encoder is `torch.bfloat16`. The VAE and text encoder can also be `torch.float32` or `torch.float16`.
   - For guidance-distilled variants of LTX-Video, set `guidance_scale` to `1.0`. The `guidance_scale` for any other model should be set higher, like `5.0`, for good generation quality.
   - For timestep-aware VAE variants (LTX-Video 0.9.1 and above), set `decode_timestep` to `0.05` and `image_cond_noise_scale` to `0.025`.
-  - For variants that support interpolation between multiple conditioning images and videos (LTX-Video 0.9.5 and above), use similar images and videos for the best results. Divergence from the conditioning inputs may lead to abrupt transitionts in the generated video.
+  - For variants that support interpolation between multiple conditioning images and videos (LTX-Video 0.9.5 and above), use similar images and videos for the best results. Divergence from the conditioning inputs may lead to abrupt transitions in the generated video.
 
 - LTX-Video 0.9.7 includes a spatial latent upscaler and a 13B parameter transformer. During inference, a low resolution video is quickly generated first and then upscaled and refined.
 
@@ -329,7 +329,7 @@ export_to_video(video, "output.mp4", fps=24)
 
   <details>
   <summary>Show example code</summary>
-  
+
   ```python
   import torch
   from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
@@ -474,6 +474,12 @@ export_to_video(video, "output.mp4", fps=24)
 
   </details>
 
+## LTXI2VLongMultiPromptPipeline
+
+[[autodoc]] LTXI2VLongMultiPromptPipeline
+  - all
+  - __call__
+
 ## LTXPipeline
 
 [[autodoc]] LTXPipeline

src/diffusers/__init__.py

@@ -353,6 +353,7 @@
             "KDPM2AncestralDiscreteScheduler",
             "KDPM2DiscreteScheduler",
             "LCMScheduler",
+            "LTXEulerAncestralRFScheduler",
             "PNDMScheduler",
             "RePaintScheduler",
             "SASolverScheduler",
@@ -538,6 +539,7 @@
             "LongCatImageEditPipeline",
             "LongCatImagePipeline",
             "LTXConditionPipeline",
+            "LTXI2VLongMultiPromptPipeline",
             "LTXImageToVideoPipeline",
             "LTXLatentUpsamplePipeline",
             "LTXPipeline",
@@ -1088,6 +1090,7 @@
             KDPM2AncestralDiscreteScheduler,
             KDPM2DiscreteScheduler,
             LCMScheduler,
+            LTXEulerAncestralRFScheduler,
             PNDMScheduler,
             RePaintScheduler,
             SASolverScheduler,
@@ -1252,6 +1255,7 @@
             LongCatImageEditPipeline,
             LongCatImagePipeline,
             LTXConditionPipeline,
+            LTXI2VLongMultiPromptPipeline,
             LTXImageToVideoPipeline,
             LTXLatentUpsamplePipeline,
             LTXPipeline,

src/diffusers/pipelines/__init__.py

@@ -288,6 +288,7 @@
         "LTXImageToVideoPipeline",
         "LTXConditionPipeline",
         "LTXLatentUpsamplePipeline",
+        "LTXI2VLongMultiPromptPipeline",
     ]
     _import_structure["lumina"] = ["LuminaPipeline", "LuminaText2ImgPipeline"]
     _import_structure["lumina2"] = ["Lumina2Pipeline", "Lumina2Text2ImgPipeline"]
@@ -729,7 +730,13 @@
             LEditsPPPipelineStableDiffusionXL,
         )
         from .longcat_image import LongCatImageEditPipeline, LongCatImagePipeline
-        from .ltx import LTXConditionPipeline, LTXImageToVideoPipeline, LTXLatentUpsamplePipeline, LTXPipeline
+        from .ltx import (
+            LTXConditionPipeline,
+            LTXI2VLongMultiPromptPipeline,
+            LTXImageToVideoPipeline,
+            LTXLatentUpsamplePipeline,
+            LTXPipeline,
+        )
         from .lucy import LucyEditPipeline
         from .lumina import LuminaPipeline, LuminaText2ImgPipeline
         from .lumina2 import Lumina2Pipeline, Lumina2Text2ImgPipeline

src/diffusers/pipelines/ltx/__init__.py

@@ -25,6 +25,7 @@
     _import_structure["modeling_latent_upsampler"] = ["LTXLatentUpsamplerModel"]
     _import_structure["pipeline_ltx"] = ["LTXPipeline"]
     _import_structure["pipeline_ltx_condition"] = ["LTXConditionPipeline"]
+    _import_structure["pipeline_ltx_i2v_long_multi_prompt"] = ["LTXI2VLongMultiPromptPipeline"]
     _import_structure["pipeline_ltx_image2video"] = ["LTXImageToVideoPipeline"]
     _import_structure["pipeline_ltx_latent_upsample"] = ["LTXLatentUpsamplePipeline"]
 
@@ -39,6 +40,7 @@
         from .modeling_latent_upsampler import LTXLatentUpsamplerModel
         from .pipeline_ltx import LTXPipeline
         from .pipeline_ltx_condition import LTXConditionPipeline
+        from .pipeline_ltx_i2v_long_multi_prompt import LTXI2VLongMultiPromptPipeline
         from .pipeline_ltx_image2video import LTXImageToVideoPipeline
         from .pipeline_ltx_latent_upsample import LTXLatentUpsamplePipeline