Spaces:
Running on Zero
Running on Zero
multimodalart HF Staff
Evoke text-to-video (t2v) demo: vendored engine + Gradio app
a8047d9 verified | title: Alaya-EVOKE Text-to-Video | |
| emoji: 🌍 | |
| colorFrom: yellow | |
| colorTo: pink | |
| sdk: gradio | |
| sdk_version: 5.49.1 | |
| python_version: "3.10" | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| short_description: Text-to-video world model (Evoke, 14B DiT, 3-step distilled) | |
| startup_duration_timeout: 60m | |
| models: | |
| - SII-YuanyangYin/Evoke | |
| tags: | |
| - text-to-video | |
| - world-model | |
| - video-generation | |
| # Alaya-EVOKE · Text-to-Video | |
| Prompt-only **text-to-video** demo of the released **post-distillation** checkpoint of | |
| [**SII-YuanyangYin/Evoke**](https://huggingface.co/SII-YuanyangYin/Evoke) — *Alaya-EVOKE: From | |
| Linear-Scaling Supervision to Endless World*. | |
| - **14B DiT** world model + UMT5 text encoder + Wan VAE | |
| - Sampled in **3 steps, no CFG** (the distilled recipe) at **384×640 · 24 fps** | |
| - This is the model's **`t2v`** mode: no camera control (the pipeline runs warp-free), so the clip | |
| is generated from the prompt alone. One chunk ≈ 1.5 s of video. | |
| The demo drives the authors' own inference engine (`scripts/inference/infer_single.py`) in-process, | |
| reproducing the `infer_post_distill.sh MODE=t2v` recipe exactly | |
| (`STAGE2_STEPS=1 1 1`, `guidance_scale=1.0`, `vae_decode_type=persistent`). | |
| > Note: the distilled checkpoints were trained on `v2v` conditioning, so `t2v` here is zero-shot | |
| > extrapolation (as documented upstream) — expect it to work but not to be the model's trained mode. | |
| Model & code © the Evoke authors, Apache-2.0. | |