Aller au contenu
WorkflowPrésentéExterne
Ouvrir la source

Efficient first-last frame video generation workflow: 5 seconds per segment, and can generate continuously up to 15 seconds. — v1.0

This workflow is a first-last frame video workflow based on the remix2.1 (high noise) + Dasiwa (low noise) models. Each segment generates 5s (81 frames, 16fps). Videos up to 15s can be created in one run by...

VersionRelease 2642987 — 02µÚ¶þÆÚÊÕβ֡ÊÓÆµ´©Ô½µçÓ°.jsonEstimé VRAMNot yet characterizedDClasse

Profil d'exécution

Accès
Flux de travail externe
Statut
Présenté
Version
02µÚ¶þÆÚÊÕβ֡ÊÓÆµ´©Ô½µçÓ°.json
Source
Civitai
Mis à jour
14 oct. 2026

Description de la source

Instructions for Use

  1. This workflow is a first-last frame video workflow based on the remix2.1 (high noise) + Dasiwa (low noise) models. Each segment generates 5s (81 frames, 16fps). Videos up to 15s can be created in one run by connecting segments. Its key advantage: the high-noise model controls motion, the low-noise model controls details, delivering excellent overall results.

2.To use, upload the first and last frame images, connect the nodes as needed, then start generation. If you only need one 5‐second first‐last frame segment, you can disable the others (there is a toggle switch).

  1. The high-noise model uses remix2.1 by Feihou (strong motion control). The low-noise model uses Dasiwa (specialized anime model, outstanding for detail refinement). Dasiwa effectively reduces the face inconsistency issue native to remix2.1.

  2. The acceleration feature requires a compatible environment and GPU version (limited by architecture; e.g., not supported on RTX 2060 Super). If errors occur during runtime, disable this feature — the speed impact is minimal.

  3. Resolution settings: use default for local runs; lower if you encounter out-of-memory errors. Can be increased slightly for online runs. A built-in image scaling node prevents lag from oversized input images.

  4. Inference steps (optimized for Wan2.2):

  • High-noise model: 2 steps (motion control)

  • Low-noise model: 4 steps (detail control)

This gives the best balance of quality and speed. Example: 5s video takes ~6 minutes on an RTX 5060 Ti 16GB.

  1. Prompts: To use custom prompts, disconnect the corresponding node and enter text manually based on the image content.

  2. VRAM/ROM cleanup node: Enable when your device is under heavy load to reduce memory pressure.

  3. Frame interpolation: Automatically upsamples video from 16fps to 32fps, fast and high-quality.


Model Links

This workflow is available for free online testing; download it for local use if you find it useful:

Use the workflow online: https://www.runninghub.ai/post/2016068464221364225/?inviteCode=rh-v1443

Generate a group photo: https://www.runninghub.ai/ai-detail/2015758255749865474/?inviteCode=rh-v1443

What you need

Model files
13.3 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Exigences

Modèles

5
  • DasiwaWAN22I2V14BV8V1_tastysinLowV81.safetensors

    Non résolu

    Checkpoint · Unknown

  • rife47.pth

    Fichier non vérifié

    Checkpoint · Unknown

  • umt5_xxl_fp16.safetensors

    Possible

    Text encoder · Unknown

  • wan_2.1_vae.safetensors

    Fichier non vérifié

    VAE · Unknown

  • Checkpoint · 13.3 GB · SAFETENSORS · Unknown

Packs de nœuds

6
  • ComfyUI_Comfyroll_CustomNodes

    Trouvé

    Pack de nœud · Registry

  • comfyui_layerstyle

    Trouvé

    Pack de nœud · Registry

  • comfyui_memory_cleanup

    Trouvé

    Pack de nœud · Registry

  • comfyui-frame-interpolation

    Trouvé

    Pack de nœud · Registry

  • Pack de nœud · Registry

  • comfyui-videohelpersuite

    Trouvé

    Pack de nœud · Registry

Sources

1 source
CivitaiPrincipalVersion 2642987
civitai.com/models/2349859

Vérifié 14 oct.

Extraits de sources

1 extrait

Source context: 942 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B