Filter by type:
Filter by tags:
vllm-omni-wan2.2-i2v
Wan2.2-I2V-A14B via vLLM-Omni - Image-to-video generation model from Wan-AI. Generates high-quality videos from images using a 14B parameter diffusion model.
Repository: localaiLicense: apache-2.0
longcat-video
LongCat-Video served by LocalAI's dedicated CUDA backend. Generates video
from a text prompt or a start image. The SDPA attention path works without
FlashAttention and is suitable for CUDA 13 ARM64 systems such as DGX Spark.
This is a very large checkpoint (roughly 83 GB in Hugging Face storage) and
requires Linux with an NVIDIA CUDA GPU plus substantial memory and disk.
Repository: localaiLicense: mit
longcat-video-avatar-1.5
LongCat-Video-Avatar-1.5 served by LocalAI's dedicated CUDA backend. Turns
speech plus a prompt into an avatar video, optionally conditioning on a
portrait, and continues across multiple segments for longer audio.
Avatar generation also loads tokenizer, text encoder, and VAE components
from LongCat-Video. Plan for very large downloads and substantial NVIDIA
GPU or unified memory; CPU and macOS execution are unsupported.
Repository: localaiLicense: mit
minimax-h3-fl2va-q4
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates
video AND audio jointly from a text prompt, so a clip comes back as an MP4
with a real soundtrack rather than a silent render: ask for speech in the
prompt and the model lip-syncs it.
This is the Q4_K_M quantisation of the FL2VA partition, which serves
text-to-video (t2va) and first/last-frame conditioning (fl2va). Reference
conditioning (ref2va) is a different checkpoint and is refused by this one.
Roughly 40 GB of weights across five files, plus the two VAE configs that
carry the latent statistics. The default canvas is 1344x768
at 124 frames and 24 fps, about 5.2 seconds. Generation is slow — measured
at roughly 176 s per denoise step at that canvas on a 20-SM device, so the
50-step default is a multi-hour job. Muxing the finished frames needs
ffmpeg on the host.
Repository: localaiLicense: other
minimax-h3-ref2va-q4
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates
video AND audio jointly, so a clip comes back as an MP4 with a real
soundtrack rather than a silent render.
This is the Q4_K_M quantisation of the Ref2VA partition, the one that takes
REFERENCE conditioning: a reference image, a reference clip, or reference
audio, prepended as their own blocks so the subject or style carries into the
generated video. For plain text-to-video or first/last-frame conditioning use
minimax-h3-fl2va-q4 instead - the two partitions are separate checkpoints and
each refuses the other's tasks.
Use this Q4_K_M build, NOT the NVFP4 Ref2VA weights: NVFP4 renders a
multicolour patch grid, and it took three investigations upstream to
establish that the fault is the quantisation rather than the reference path.
On Q4_K_M the same code renders coherently.
Roughly 40 GB of weights across five files, plus the two VAE configs that
carry the latent statistics. The default canvas is 1344x768 at 124 frames and
24 fps, about 5.2 seconds. Generation is slow - roughly 176 s per denoise
step at that canvas on a 20-SM device, so the 50-step default is a multi-hour
job. Muxing the finished frames needs ffmpeg on the host.
Repository: localaiLicense: other
ltx-2
**LTX-2** is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution.
**Key Features:**
- **Joint Audio-Video Generation**: Generates synchronized video and audio in a single model
- **Image-to-Video**: Converts static images into dynamic videos with matching audio
- **High Quality**: Produces realistic video with natural motion and synchronized audio
- **Open Weights**: Available under the LTX-2 Community License Agreement
**Model Details:**
- **Model Type**: Diffusion-based audio-video foundation model
- **Architecture**: DiT (Diffusion Transformer) based
- **Developed by**: Lightricks
- **Paper**: [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://arxiv.org/abs/2601.03233)
**Usage Tips:**
- Width & height settings must be divisible by 32
- Frame count must be divisible by 8 + 1 (e.g., 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97, 105, 113, 121)
- Recommended settings: width=768, height=512, num_frames=121, frame_rate=24.0
- For best results, use detailed prompts describing motion and scene dynamics
**Limitations:**
- This model is not intended or able to provide factual information
- Prompt following is heavily influenced by the prompting-style
- When generating audio without speech, the audio may be of lower quality
**Citation:**
```bibtex
@article{hacohen2025ltx2,
title={LTX-2: Efficient Joint Audio-Visual Foundation Model},
author={HaCohen, Yoav and Brazowski, Benny and Chiprut, Nisan and others},
journal={arXiv preprint arXiv:2601.03233},
year={2025}
}
```
Repository: localaiLicense: ltx-2-community-license-agreement
wan-2.1-i2v-14b-480p-ggml
Wan 2.1 I2V 14B 480P — image-to-video diffusion, GGUF Q4 quantization.
Animates a reference image into a 33-frame 480p clip. Requires more
RAM than the 1.3B T2V variant; CPU offload enabled by default.
Repository: localaiLicense: apache-2.0
wan-2.1-flf2v-14b-720p-ggml
Wan 2.1 FLF2V 14B 720P — first-last-frame-to-video diffusion, GGUF Q4_K_M.
Takes a start and end reference image and interpolates a 33-frame clip
between them. Unlike the plain I2V variant this model feeds the end
frame through clip_vision as well, so it conditions semantically (not
just in pixel-space) on both endpoints. That makes it the right choice
for seamless loops (start_image == end_image) and clean narrative cuts.
Native 720p but accepts 480p resolutions; shares the same VAE, t5xxl
text encoder, and clip_vision_h as I2V 14B.
Repository: localaiLicense: apache-2.0
wan-2.1-i2v-14b-720p-ggml
Wan 2.1 I2V 14B 720P — image-to-video diffusion, GGUF Q4_K_M.
Native 720p sibling of the 480p I2V model: animates a single
reference image into a 33-frame clip at up to 1280x720. Trained
purely as image-to-video (no first-last-frame interpolation path),
so motion is freer and better-suited to single-anchor animation
than repurposing the FLF2V 720P variant for i2v. Shares the same
VAE, umt5_xxl text encoder, and clip_vision_h as the I2V 14B 480P
and FLF2V 14B 720P entries.
Repository: localaiLicense: apache-2.0
ltx-2.3
**LTX-2.3** is an improved DiT-based audio-video foundation model from Lightricks, building upon the LTX-2 architecture with enhanced capabilities for generating synchronized video and audio within a single model.
**Key Features:**
- **Joint Audio-Video Generation**: Generates synchronized video and audio in a single model
- **Image-to-Video**: Converts static images into dynamic videos with matching audio
- **Enhanced Quality**: Improved video quality and motion generation over LTX-2
- **Open Weights**: Available under the LTX-2 Community License Agreement
**Model Details:**
- **Model Type**: Diffusion-based audio-video foundation model
- **Architecture**: DiT (Diffusion Transformer) based
- **Developed by**: Lightricks
- **Parent Model**: LTX-2
**Usage Tips:**
- Width & height settings must be divisible by 32
- Frame count must be divisible by 8 + 1 (e.g., 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97, 105, 113, 121)
- Recommended settings: width=768, height=512, num_frames=121, frame_rate=24.0
- For best results, use detailed prompts describing motion and scene dynamics
**Limitations:**
- This model is not intended or able to provide factual information
- Prompt following is heavily influenced by the prompting-style
- When generating audio without speech, the audio may be of lower quality
Repository: localaiLicense: ltx-2-community-license-agreement
ltx-2.3-22b-dev-ggml
LTX-2.3 22B dev - DiT-based audio-video foundation model from Lightricks,
GGUF-quantized for the stable-diffusion.cpp backend. Generates synchronized
video and audio from a text prompt (T2V), a reference image (I2V), or
first/last frame pairs (FLF2V). Uses gemma-3-12b-it as the text encoder
and ships dedicated video and audio VAEs plus an embeddings_connectors
safetensors that bridges the LLM hidden states to the diffusion model.
This entry uses the dynamic (UD) Q4_K_M quantization of the 22B model
(~16 GB) paired with the UD-Q4_K_XL QAT Gemma encoder (~7.4 GB).
Recommended generation: width=1280, height=720, video_frames=33,
fps=24, sampler=euler, cfg_scale=6.0.
Repository: localaiLicense: ltx-2-community-license-agreement
ltx-2.3-22b-dev-ggml-q4_k_m
LTX-2.3 22B dev - non-dynamic Q4_K_M quantization (~14.3 GB). Same
pipeline as ltx-2.3-22b-dev-ggml but with the plain Q4_K_M weights
instead of the dynamic UD-Q4_K_M variant. Slightly smaller and slightly
lower quality.
Repository: localaiLicense: ltx-2-community-license-agreement
ltx-2.3-22b-dev-ggml-q8_0
LTX-2.3 22B dev - Q8_0 quantization (~22.8 GB). Highest-quality
quantized dev variant on the cpp backend; needs roughly twice the
VRAM/RAM of the Q4 entries but produces noticeably cleaner audio
and motion. Paired with the QAT Gemma-3 12B encoder.
Repository: localaiLicense: ltx-2-community-license-agreement
ltx-2.3-22b-distilled-ggml
LTX-2.3 22B distilled - faster student of the dev model, GGUF-quantized
for the stable-diffusion.cpp backend. Trades a small amount of quality
for substantially fewer sampling steps, making it the right pick for
iterative previews and CPU-offloaded inference. Same input modalities
as the dev entry (T2V / I2V / FLF2V) and the same gemma-3-12b-it text
encoder.
This entry uses the dynamic (UD) Q4_K_M quantization of the 22B
distilled model (~16.3 GB). Recommended generation: width=1280,
height=720, video_frames=33, fps=24, sampler=euler, cfg_scale=6.0.
Repository: localaiLicense: ltx-2-community-license-agreement
ltx-2.3-22b-distilled-ggml-q4_k_m
LTX-2.3 22B distilled - non-dynamic Q4_K_M quantization (~14.3 GB).
Same pipeline as ltx-2.3-22b-distilled-ggml but with the plain Q4_K_M
weights instead of the dynamic UD-Q4_K_M variant.
Repository: localaiLicense: ltx-2-community-license-agreement
ltx-2.3-22b-distilled-ggml-q8_0
LTX-2.3 22B distilled - Q8_0 quantization (~22.8 GB). Highest-quality
distilled variant on the cpp backend; useful when you want the
distilled sampling cost but the cleanest possible output.
Repository: localaiLicense: ltx-2-community-license-agreement