Aller au contenu
WorkflowPrésentéExterne
Télécharger

4step 3 Video Looper — v1.1

changed where the image reference for the color match subgraph is inserted so it takes the color from the resized image rather than the original input image. this should make the color matching feature more consistent.

Sourcecivitai.com/models/2529191
VersionRelease 2849559 — TrashAI_Video_Better_Looper.jsonEstimé VRAMNot yet characterizedUnratedClasse

Profil d'exécution

Accès
Flux de travail externe
Statut
Présenté
Version
TrashAI_Video_Better_Looper.json
Source
Civitai
Mis à jour
4 nov. 2026

Description de la source

changed where the image reference for the color match subgraph is inserted so it takes the color from the resized image rather than the original input image. this should make the color matching feature more consistent.

changed what frames are trimmed, added another interpolation section before the interpolation group so that it adds frames to make the video loop more consistently before turning on interpolation feature. not trimming the frames allowing the rife node to insert a frame between the end and start of where video C loops to A for a smoother more seamless loop. its a small change some might not notice a difference but i do so i wanted to push an update on this through.

What you need

Model files
2.3 GiB known subtotal

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

Exigences

Modèles

8

  • 2x-AnimeSharpV4_Fast_RCAN_PU.safetensors

    Non résoluOptionnel

    Upscaler · Unknown

  • DasiwaWAN22I2V14BLightspeed_boundbiteHighV10.safetensors

    Non résolu

    Diffusion model · Unknown

  • DasiwaWAN22I2V14BLightspeed_boundbiteLowV10.safetensors

    Non résolu

    Diffusion model · Unknown

  • rife49.pth

    Trouvé

    Checkpoint · 20.4 MB · PTH · Unknown

  • umt5_xxl_fp8_e4m3fn_scaled.safetensors

    Dépôt identifié

    Text encoder · Unknown

  • wan_2.1_vae.safetensors

    Dépôt identifié

    VAE · Unknown

  • wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors

    Trouvé

    LoRA · 1.14 GB · SAFETENSORS · FP32 + I64 (tensor header) · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged

  • wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors

    Trouvé

    LoRA · 1.14 GB · SAFETENSORS · FP32 + I64 (tensor header) · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged

Packs de nœuds

11

  • comfyui-custom-scripts

    Trouvé

    Pack de nœud · Registry

  • comfyui-easy-use

    Trouvé

    Pack de nœud · Registry

  • Trouvé

    Pack de nœud · Registry

  • comfyui-kjnodes

    Trouvé

    Pack de nœud · Registry

  • comfyui-videohelpersuite

    Trouvé

    Pack de nœud · Registry

  • Fast Groups Bypasser (rgthree)

    Non résolu

    Pack de nœud · Unknown

  • Label (rgthree)

    Non résolu

    Pack de nœud · Unknown

  • Mute / Bypass Relay (rgthree)

    Non résoluOptionnel

    Pack de nœud · Unknown

  • Mute / Bypass Repeater (rgthree)

    Non résoluOptionnel

    Pack de nœud · Unknown

  • rgthree-comfy

    Trouvé

    Pack de nœud · Registry

  • whiterabbit

    Trouvé

    Pack de nœud · Registry

Sources

1 source
CivitaiPrincipalVersion 2849559
civitai.com/models/2529191

Vérifié 4 nov.

Workflow instructions

Author notes from TrashAI_Video_Better_Looper.json · selected release

## How It Works Simple 4 step looper. This workflow generates **3 videos** that seamlessly loop together: 1. **Video 1 (i2v)**: Frame A → Frame B 2. **Video 2 (i2v)**: Frame B → Frame C (uses last frame from Video 1) 3. **Video 3 (FLF2V)**: Frame C → Frame A (uses First-Last-Frame-to-Video to return to start) The result is one continuous seamless loop! ## Quick Start 1. Upload your source image (Frame A) 2. Select resolution stage (1-10) 3. Write your prompt 4. Enable desired features (Color Match, Interpolation, Upscale) 5. Generate! ## Specs - **81 frames per video** × 3 = 243 total frames - **24 FPS** base → **48 FPS** after interpolation - Resolution auto-calculates to nearest div16 for WAN ## Requirements - ComfyUI-VideoHelperSuite - rgthree-comfy - Comfyui-WhiteRabbit - ComfyUI-KJNodes - ComfyUI-Easy-Use - ComfyUI-Frame-Interpolation - ComfyUI-Custom-Scripts

Author notes from TrashAI_Video_Better_Looper.json · selected release

| Stage | MP | Quality | |---:|---:|---:| | 1 | 0.25 | ~360p Preview | | 2 | 0.33 | ~432p Fast | | 3 | 0.40 | ~480p SD | | 4 | 0.60 | ~576p SD+ | | 5 | 0.72 | ~640p HD | | 6 | 0.85 | ~720p HD | | 7 | 1.05 | ~768p THD | | 8 | 1.15 | ~800p THD+ | | 9 | 1.30 | ~900p HQ | | 10 | 2.07 | ~1080p FHD |

Download files

Artefacts du modèle

2 artefacts

4step3VideoLooper_v11.zip

zip · 21,7 KB · SHA-256 23a0849594ba…8cd4 · Civitai

Download file

TrashAI_Video_Better_Looper.json

json · 195 KB · SHA-256 37ed698e1d8c…04dc

Download file

Extraits de sources

2 extraits
Note4 nov.civitai.com/models/2529191

Source context: 370 downloads · Type Workflows · Base model Wan Video 14B i2v 720p

Note13 oct.civitai.com/models/2529191

Source context: 359 downloads · Type Workflows · Base model Wan Video 14B i2v 720p