WorkflowListedExternal

skyreels-hunyuan-I2V-workflow — v1.0

update your Comfyui to latest version the commit for this model was yesterday !

TaskImage to videoFamilyFLUXVersionRelease 1440307 — SkyReels-V1-Hunyuan_comfy.jsonEstimated VRAMEstimate unavailableBgrade

Runtime profile

Access: External workflow
Status: Listed
Version: SkyReels-V1-Hunyuan_comfy.json
Source: Civitai
Updated: Jul 20, 2026

Source description

wlc to connect

https://www.linkedin.com/in/abdallah-issac/

***update your Comfyui to latest version the commit for this model was yesterday !

*** (VHS)use this to see your video while process (it good to cancel unwnated result and save your time)

https://civitai.com/images/59092666

***an update of kijai workflow

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

Use skyreels-hunyuan-I2V-workflow — v1.0 in ComfyUI to create a video from a selected image and text prompt.

Flow

Named components include LoadImage, CLIPTextEncode, EmptyHunyuanLatentVideo, SamplerCustom, VAEDecodeTiled, and VHS_VideoCombine.
It is listed as a Workflows item from AbdallahAlswa80, using Flux.1 D as its base model.

Inputs and outputs

Use LoadImage for the image input and CLIPTextEncode for text input; VHS_VideoCombine is named for combining video.

Setup

Update ComfyUI to the latest version before use.
Suggestion · not verified

Dependencies

Before use, check that these model files are available: clip_l.safetensors, e5m2-skyreels_hunyuan_i2v_bf16.safetensors, hunyuan_video_vae_bf16.safetensors, llava_llama3_fp8_scaled.safetensors, and skyreels-hunyuan-I2V-Q4_K_S.gguf.
Suggestion · not verified
Check for these named nodes: ApplyFirstBlockCachePatch, BasicScheduler, CLIPTextEncode, ColorMatch, ConditioningZeroOut, DualCLIPLoader, EmptyHunyuanLatentVideo, FluxGuidance, ImageNoiseAugmentation, ImageResize+, and InstructPixToPixConditioning.
Suggestion · not verified
Also check for KSamplerSelect, LoadImage, ModelSamplingSD3, PatchModelPatcherOrder, SamplerCustom, SplitSigmas, UNETLoader, UnetLoaderGGUF, VAEDecodeTiled, VAELoader, and VHS_VideoCombine.
Suggestion · not verified

Configuration

Start each prompt with FPS-24.
Suggestion · not verified
Choose the image carefully, and keep the prompt short and close to the image.
Suggestion · not verified
To use LoRAs, enable the node shown for that option.
Suggestion · not verified

Cautions

No license is listed for this workflow.
Do not use GPTs with this workflow.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiSourceVersion 1440307

civitai.com/models/1276735

Verified Aug 7

Source excerpts

2 excerpts

NoteAug 7civitai.com/models/1276735

Source context: 667 downloads · Type Workflows · Base model Flux.1 D

NoteJul 20civitai.com/models/1276735