Instructions to use realrebelai/LingBot_ComfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use realrebelai/LingBot_ComfyUI with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("realrebelai/LingBot_ComfyUI", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
LingBot-Video-Dense-1.3B β ComfyUI repack (single-file, 8GB-VRAM ready)
UPDATE! - added a prompt rebuilder node to satisfy the models need for a VERY strict json structure. this is not normal json, its what i like to call "LingBot" json prompting as its alot more in depth. try it out!
Repackaged weights of robbyant/lingbot-video-dense-1.3b for use with the ComfyUI_Rebels_LingBot node pack. No weight modification β the original diffusers shards are merged/renamed into single files for ComfyUI's model folders. All configs ship inside the node pack.
Runs T2V and TI2V on an RTX 3070 8GB / 16GB RAM: the Qwen3-VL encoder is loaded on CPU, used, and freed before the 1.3B DiT (2.79GB bf16, fully VRAM-resident) starts.
Files
| File | Put in | Size |
|---|---|---|
LingBot_1.3b_DiT.safetensors |
ComfyUI/models/diffusion_models/ |
~2.8 GB |
LingBot_text-encoder.safetensors |
ComfyUI/models/text_encoders/ |
~8 GB |
LingBot_vae.safetensors |
ComfyUI/models/vae/ |
~0.5 GB |
The text encoder is the repo's Qwen3-VL, shards merged into one file (bit-identical
tensors). lm_head.weight is intentionally absent β it is tied to embed_tokens; the
node pack re-ties it at load.
Recommended settings
- 832Γ480, up to 81 frames, 40 steps, shift 3.0
- guidance 3.0 (t2v) / ~3.0 (TI2V β higher burns color on image runs)
- export at 24 fps
- VAE tiling off unless you must (temporal color/exposure drift on long clips)
~14 s/it on a 3070 at the settings above (sequential CFG); β10 minutes per 81-frame clip.
Notes & limitations
- The trained window is 81 frames; longer generations collapse.
- Square/other aspect ratios are out-of-distribution (letterboxing artifacts) β stay at 832Γ480.
- 1.3B-class video: modest motion complexity; rendered text (signs/labels) is not legible.
- TI2V requires the image to be fed to both the encode node (vision conditioning) and the sampler (first-frame latent) in the node pack's workflow.
License
Weights inherit the upstream LingBot-Video license (see license_link). This repo is
a format repack only; review the upstream terms before commercial use or redistribution.
Repack + nodes by RealRebelAI.
- Downloads last month
- -
Model tree for realrebelai/LingBot_ComfyUI
Base model
robbyant/lingbot-video-dense-1.3b