---
title: LTX-2.3-Diffusers
canonical_url: "https://www.modelscope.cn/models/hf-diffusers/LTX-2.3-Diffusers"
md_url: "https://www.modelscope.cn/models/hf-diffusers/LTX-2.3-Diffusers.md"
repository: hf-diffusers/LTX-2.3-Diffusers
last_updated: 2026-05-21
license: other
pipeline_tag: image-to-video
tasks:
  - image-to-video
base_model:
  - Lightricks/LTX-2.3
base_model_relation: finetune
parameters: 38.4B
tensor_type:
  - BF16
  - F32
library_name:
  - pytorch
  - safetensors
  - diffusers
frameworks:
  - pytorch
downloads: 421
stars: 1
tags:
  - image-to-video
  - text-to-video
  - video-to-video
  - image-text-to-video
  - audio-to-video
  - text-to-audio
  - video-to-audio
  - audio-to-audio
  - text-to-audio-video
  - image-to-audio-video
  - image-text-to-audio-video
  - ltx-2
  - ltx-2-3
  - ltx-video
  - ltxv
  - lightricks
---

# LTX-2.3-Diffusers

> LTX-2.3-Diffusers - hf-diffusers 在 ModelScope 开源的模型。Diffusers-format weights for Lightricks/LTX-2.3 — a DiT-based foundation model that jointly generates synchronized video and audio.

hf-diffusers/LTX-2.3-Diffusers 是 ModelScope 魔搭社区上的 38.4B 参数image-to-video模型，采用 other 许可，基于 Lightricks/LTX-2.3 构建。

- **Repository**: hf-diffusers/LTX-2.3-Diffusers
- **License**: other
- **Tasks**: image-to-video
- **Parameters**: 38.4B
- **Base model**: Lightricks/LTX-2.3
- **Tags**: image-to-video, text-to-video, video-to-video, image-text-to-video, audio-to-video, text-to-audio, video-to-audio, audio-to-audio, text-to-audio-video, image-to-audio-video, image-text-to-audio-video, ltx-2, ltx-2-3, ltx-video, ltxv, lightricks
- **Downloads**: 421
- **Stars**: 1
- **Last updated**: 2026-05-21

Source: https://www.modelscope.cn/models/hf-diffusers/LTX-2.3-Diffusers

---

# LTX-2.3 (Diffusers)

Diffusers-format weights for [Lightricks/LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3) — a DiT-based foundation model that jointly generates synchronized video and audio.

A distilled variant (8 steps, CFG=1) is available at [`diffusers/LTX-2.3-Distilled-Diffusers`](https://huggingface.co/diffusers/LTX-2.3-Distilled-Diffusers).

## Usage

Requires a recent build of `diffusers` with LTX-2 support:

```bash
pip install -U git+https://github.com/huggingface/diffusers
```

### Text-to-video + audio

```python
import torch
from diffusers import LTX2Pipeline
from diffusers.pipelines.ltx2.export_utils import encode_video
from diffusers.pipelines.ltx2.utils import DEFAULT_NEGATIVE_PROMPT

pipe = LTX2Pipeline.from_pretrained(
    "diffusers/LTX-2.3-Diffusers", torch_dtype=torch.bfloat16
)
pipe.enable_model_cpu_offload()

prompt = "A flowing river in a forest at golden hour, gentle wind in the leaves."
frame_rate = 24.0

video, audio = pipe(
    prompt=prompt,
    negative_prompt=DEFAULT_NEGATIVE_PROMPT,
    width=768,
    height=512,
    num_frames=121,
    frame_rate=frame_rate,
    num_inference_steps=30,
    guidance_scale=3.0,
    output_type="np",
    return_dict=False,
)

encode_video(
    video[0],
    fps=frame_rate,
    audio=audio[0].float().cpu(),
    audio_sample_rate=pipe.vocoder.config.output_sampling_rate,
    output_path="ltx2_t2v.mp4",
)
```

### First-last-frame-to-video (FLF2V)

```python
import torch
from diffusers import LTX2ConditionPipeline
from diffusers.pipelines.ltx2.pipeline_ltx2_condition import LTX2VideoCondition
from diffusers.pipelines.ltx2.utils import DEFAULT_NEGATIVE_PROMPT
from diffusers.utils import load_image

pipe = LTX2ConditionPipeline.from_pretrained(
    "diffusers/LTX-2.3-Diffusers", torch_dtype=torch.bfloat16
)
pipe.enable_model_cpu_offload()

first_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_first_frame.png")
last_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_last_frame.png")

conditions = [
    LTX2VideoCondition(frames=first_image, index=0, strength=1.0),
    LTX2VideoCondition(frames=last_image, index=-1, strength=1.0),
]

prompt = "CG animation style, a small blue bird takes off from the ground, flapping its wings."
frame_rate = 24.0

video = pipe(
    conditions=conditions,
    prompt=prompt,
    negative_prompt=DEFAULT_NEGATIVE_PROMPT,
    width=768,
    height=512,
    num_frames=121,
    frame_rate=frame_rate,
    num_inference_steps=40,
    guidance_scale=4.0,
    output_type="np",
    return_dict=False,
)
```

### IC-LoRA (camera control)

```python
import torch
from diffusers import LTX2InContextPipeline
from diffusers.pipelines.ltx2.export_utils import encode_video
from diffusers.pipelines.ltx2.utils import DEFAULT_NEGATIVE_PROMPT

pipe = LTX2InContextPipeline.from_pretrained(
    "diffusers/LTX-2.3-Diffusers", torch_dtype=torch.bfloat16
)
pipe.enable_model_cpu_offload()
pipe.load_lora_weights(
    "Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-In",
    adapter_name="ic_lora",
    weight_name="ltx-2-19b-lora-camera-control-dolly-in.safetensors",
)
pipe.set_adapters("ic_lora", 1.0)

prompt = "A flowing river in a forest"
frame_rate = 24.0

video, audio = pipe(
    prompt=prompt,
    negative_prompt=DEFAULT_NEGATIVE_PROMPT,
    width=768,
    height=512,
    num_frames=121,
    frame_rate=frame_rate,
    num_inference_steps=30,
    guidance_scale=3.0,
    output_type="np",
    return_dict=False,
)

encode_video(
    video[0],
    fps=frame_rate,
    audio=audio[0].float().cpu(),
    audio_sample_rate=pipe.vocoder.config.output_sampling_rate,
    output_path="ltx2_ic_lora.mp4",
)
```

## Notes

- `width` and `height` must be divisible by 32; `num_frames` must equal `8k + 1`.
- See the [Diffusers LTX-2 docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx2) for multimodal guidance, prompt enhancement, and the upscaling/refinement pipeline.

## License

These weights are released under the [LTX Video 2 Open Source License](https://huggingface.co/Lightricks/LTX-2.3/blob/main/LICENSE).