Filter by type:
Filter by tags:
vllm-omni-wan2.2-t2v
Wan2.2-T2V-A14B via vLLM-Omni - Text-to-video generation model from Wan-AI. Generates high-quality videos from text prompts 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
minimax-h3-fl2va-unpruned-q4-ggml
MiniMax-H3 served by stable-diffusion.cpp. It generates video AND stereo
audio jointly from a text prompt, so a clip comes back as an MP4 with a
soundtrack. Muxing the finished frames needs ffmpeg on the host.
Runtime: stable-diffusion.cpp (backend stablediffusion-ggml). Partition:
fl2va. DiT layout: unpruned. Format: Q4_K_M.
This entry is the FL2VA partition: text-to-video, first-frame (I2VA) and first/last-frame (FL2VA) conditioning. It refuses reference conditioning (reference image or audio): that needs minimax-h3-ref2va-pruned-q4-ggml, which is a separate checkpoint.
Render status: verified render (the stable-diffusion.cpp page shows a text-to-video and
an image-to-video render with this file).
Weights are the Q4_K_M quantisation of the DiT (~18.8 GB), the
Qwen3-VL-32B MiniMax-H3 text encoder (~18 GB), the fp16 video VAE (~5 GB)
and the fp32 audio VAE (~0.6 GB). MiniMax-H3 runs at 24 fps and the width
and height are rounded up to a multiple of 32. The frame count is
rounded up to the 17k + 5 grid.
Repository: localaiLicense: other
minimax-h3-fl2va-pruned-q4-ggml
MiniMax-H3 served by stable-diffusion.cpp. It generates video AND stereo
audio jointly from a text prompt, so a clip comes back as an MP4 with a
soundtrack. Muxing the finished frames needs ffmpeg on the host.
Runtime: stable-diffusion.cpp (backend stablediffusion-ggml). Partition:
fl2va. DiT layout: pruned. Format: Q4_K_M.
This entry is the FL2VA partition: text-to-video, first-frame (I2VA) and first/last-frame (FL2VA) conditioning. It refuses reference conditioning (reference image or audio): that needs minimax-h3-ref2va-pruned-q4-ggml, which is a separate checkpoint. It is the smaller, pruned counterpart of minimax-h3-fl2va-unpruned-q4-ggml.
Render status: rendered with stable-diffusion.cpp on CUDA (text-to-video, 512x288, 22 frames, with audio). Not yet rendered through LocalAI.
Weights are the Q4_K_M quantisation of the DiT (~11.4 GB), the
Qwen3-VL-32B MiniMax-H3 text encoder (~18 GB), the fp16 video VAE (~5 GB)
and the fp32 audio VAE (~0.6 GB). MiniMax-H3 runs at 24 fps and the width
and height are rounded up to a multiple of 32. The frame count is
rounded up to the 17k + 5 grid.
Repository: localaiLicense: other
minimax-h3-ref2va-pruned-q4-ggml
MiniMax-H3 served by stable-diffusion.cpp. It generates video AND stereo
audio jointly from a text prompt, so a clip comes back as an MP4 with a
soundtrack. Muxing the finished frames needs ffmpeg on the host.
Runtime: stable-diffusion.cpp (backend stablediffusion-ggml). Partition:
ref2va. DiT layout: pruned. Format: Q4_K_M.
This entry is the REF2VA partition, the one that takes REFERENCE conditioning: reference images, reference videos (a directory of frames, with an optional paired soundtrack) and reference audio steer the subject and the voice of the clip. It does not serve first/last-frame keyframes, and keyframes cannot be mixed with references. For plain text-to-video or keyframes use minimax-h3-fl2va-unpruned-q4-ggml.
Render status: verified render (the stable-diffusion.cpp page shows a reference-to-video
render with this file).
Weights are the Q4_K_M quantisation of the DiT (~11.4 GB), the
Qwen3-VL-32B MiniMax-H3 text encoder (~18 GB), the fp16 video VAE (~5 GB)
and the fp32 audio VAE (~0.6 GB). MiniMax-H3 runs at 24 fps and the width
and height are rounded up to a multiple of 32. The frame count is
rounded up to the 17k + 5 grid.
Repository: localaiLicense: other
wan-2.1-t2v-1.3b-ggml
Wan 2.1 T2V 1.3B — text-to-video diffusion model, GGUF-quantized for the
stable-diffusion.cpp backend. Generates short (33-frame) 832x480 clips
from a text prompt. Cheapest Wan variant, suitable for CPU-offloaded
inference with ~10 GB of usable RAM.
Repository: localaiLicense: apache-2.0
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