Saltar al contenido
ModelPublicadoExterno
Descargar

LingBot World V2

GGUF quantizations of robbyant/lingbot-world-v2-14b-causal-fast for ComfyUIRebelsLingBotWorld — an action-controlled world model running on consumer GPUs (tested: RTX 3070 8GB / 16GB RAM).

TipoOtherModelo baserobbyant/lingbot-world-v2-14b-causal-fastVersiónRevision 79be5d5Bcalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
484 MB–18,6 GB
Modelo base
robbyant/lingbot-world-v2-14b-causal-fast
Versión
vRevision 79be5d5
Actualizado
6 oct 2026
Descargas
7,4 mil
Fuente
Hugging Face

Descripción de la fuente

LingBot-World-v2 14B causal-fast — GGUF (8GB-VRAM ready)

GGUF quantizations of robbyant/lingbot-world-v2-14b-causal-fast for ComfyUI_Rebels_LingBotWorld — an action-controlled world model running on consumer GPUs (tested: RTX 3070 8GB / 16GB RAM).

You author a camera/movement track (or type one into the Action Builder node); the model renders the video that track produces from your start image, with genuine action following. Offline generation, chunked causal sampling, 4 distilled steps per chunk.

Files

FileNotes
LingBot-World-14B-Q4_K_S.gguf (~11.7GB)tested tier; Q5-bumped v-projections keep effective bpw ~6.7
other tiers (Q4_K_M...Q8_0)quality ladder; RAM-streamed, VRAM use is unchanged

Also required: Wan2.1_VAE.pth, a UMT5-XXL GGUF encoder (loads via ComfyUI-GGUF CLIPLoader, type wan)

Settings that matter (8GB)

  • Resolution preset 256×448 (default) or 320×544; world-memory window 6+2
  • The KV cache is the world memory: it scales with window × resolution (upstream 18+6 @ 480×832 ≈ 21GB — does not fit consumer cards; the sampler pre-checks and refuses instead of hanging)
  • frame_num 4n+1; start at 21; export 16 fps

License

CC BY-NC-SA 4.0 (inherited from upstream): non-commercial, attribution, share-alike. Quantization is a format conversion only. Quants + nodes by RealRebelAI.

https://cdn-uploads.huggingface.co/production/uploads/68761990332d15464ccc8dee/OBwm3rX-WJ5s8a-EePAbK.mp4

Fuentes

1 fuente
Hugging FacePrincipalVersión 79be5d5f30d63327ac6020ced7f653cdbc301f49
huggingface.co/realrebelai/LingBot_World_V2_ComfyUI/tree/79be5d5f30d63327ac6020ced7f653cdbc301f49

Verificado 6 oct

Artefactos del modelo

7 artefactos

LingBot-World-14B-causal-fast_merged-Q4_K_M.gguf

gguf · 11,2 GB · SHA-256 71e0ae7d4d24…94d1 · Hugging Face

Descargar

LingBot-World-14B-Q4_K_S.gguf

gguf · 10,4 GB · SHA-256 009cee1b09eb…811e · Hugging Face

Descargar

LingBot-World-14B-Q5_K_M.gguf

gguf · 12,8 GB · SHA-256 bed68e1cb79e…c9d4 · Hugging Face

Descargar

LingBot-World-14B-Q6_K.gguf

gguf · 14,4 GB · SHA-256 3d4c8d60ad1d…0acd · Hugging Face

Descargar

LingBot-World-14B-Q8_0.gguf

gguf · 18,6 GB · SHA-256 79068d70695c…efd9 · Hugging Face

Descargar

umt5-xxl-encoder-Q4_K_S.gguf

gguf · 3,26 GB · SHA-256 4a3176f32fd7…89e0 · Hugging Face

Descargar

Wan2.1_VAE.pth

pth · 484 MB · SHA-256 38071ab59bd9…d981 · Hugging Face

Descargar

Extractos de fuentes

3 extractos

--- license: cc-by-nc-sa-4.0 base_model: robbyant/lingbot-world-v2-14b-causal-fast pipeline_tag: image-to-video tags: [world-model, video, gguf, comfyui, wan, camera-control, low-vram] --- # LingBot-World-v2 14B causal-fast — GGUF (8GB-VRAM ready) GGUF quantizations of [robbyant/lingbot-world-v2-14b-causal-fast](https://huggingface.co/robbyant/lingbot-world-v2-14b-causal-fast) for **[ComfyUI_Rebels_LingBotWorld](https://github.com/RealRebelAI/ComfyUI_Rebels_LingBotWorld)** — an action-controlled world model running on consumer GPUs (tested: RTX 3070 8GB / 16GB RAM). You author a camera/movement track (or type one into the Action Builder node); the model renders the video that track produces from your start image, with genuine action following. Offline generation, chunked causal sampling, 4 distilled steps per chunk. ## Files | File | Notes | |---|---| | `LingBot-World-14B-Q4_K_S.gguf` (~11.7GB) | tested tier; Q5-bumped v-projections keep effective bpw ~6.7 | | other tiers (Q4_K_M…Q8_0) | quality ladder; RAM-streamed, VRAM use is unchanged | Also required: `Wan2.1_VAE.pth`, a **UMT5-XXL GGUF** encoder (loads via ComfyUI-GGUF CLIPLoader, type `wan`) ## Settings that matter (8GB) - Resolution preset **256×448** (default) or 320×544; world-memory window **6+2** - The KV cache is the world memory: it scales with window × resolution (upstream 18+6 @ 480×832 ≈ 21GB — does not fit consumer cards; the sampler pre-checks and refuses instead of hanging) - frame_num 4n+1; start at 21; export 16 fps ## License **CC BY-NC-SA 4.0** (inherited from upstream): non-commercial, attribution, share-alike. Quantization is a format conversion only. Quants + nodes by [RealRebelAI](https://huggingface.co/realrebelai). https://cdn-uploads.huggingface.co/production/uploads/68761990332d15464ccc8dee/OBwm3rX-WJ5s8a-EePAbK.mp4

Source context: 7427 downloads · 13 likes · Pipeline image-to-video · Repo realrebelai/LingBot_World_V2_ComfyUI

Source context: 3803 downloads · 12 likes · Pipeline image-to-video · Repo realrebelai/LingBot_World_V2_ComfyUI