---
license: apache-2.0
library_name: diffusers
pipeline_tag: text-to-video
tags:
  - longlive
  - wan
  - text-to-video
  - fastvideo
---

# LongLive 1.0 Stage 1 Diffusers

Diffusers-style LongLive stage-1 checkpoint converted from:

`/mnt/weka/home/hao.zhang/mhuo/FastVideo/LongLive/longlive_models/models/longlive_base.pt`

The model uses the causal Wan 2.1 T2V 1.3B layout. The LongLive weights replace
the transformer checkpoint; scheduler, tokenizer, text encoder, and VAE follow
`wlsaidhi/SFWan2.1-T2V-1.3B-Diffusers`.

Recommended runtime kwargs:

```yaml
model_kwargs:
  timestep_shift: 5.0
  local_attn_size: 12
  sink_size: 3
```

FastVideo training config equivalent:

```yaml
models:
  student:
    _target_: fastvideo.train.models.wan.WanCausalModel
    init_from: mignonjia/LongLive-1.0-Stage-1-Diffusers
    trainable: true

pipeline:
  flow_shift: 5
  dit_config:
    local_attn_size: 12
    sink_size: 3
```