skyreels-hunyuan-I2V-workflow — v1.0

Use skyreels-hunyuan-I2V-workflow — v1.0 in ComfyUI to turn a chosen image and text prompt into a video.

The listed components cover image loading, text encoding, latent-video setup, sampling, tiled VAE decoding, and video combination.

This v1.0 workflow is published by AbdallahAlswa80 and lists Flux.1 D as its base model.

Choose an image for LoadImage and enter a text prompt for CLIPTextEncode.

VHS_VideoCombine is listed for video handling, and the description says it can show video while processing.

Update ComfyUI to the latest version before use.

Suggestion · non vérifié

Listed model files include 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.

Named nodes include ApplyFirstBlockCachePatch, BasicScheduler, CLIPTextEncode, ColorMatch, ConditioningZeroOut, DualCLIPLoader, EmptyHunyuanLatentVideo, FluxGuidance, ImageNoiseAugmentation, ImageResize+, and InstructPixToPixConditioning.

Other named nodes are KSamplerSelect, LoadImage, ModelSamplingSD3, PatchModelPatcherOrder, SamplerCustom, SplitSigmas, UNETLoader, UnetLoaderGGUF, VAEDecodeTiled, VAELoader, and VHS_VideoCombine.

Start each prompt with FPS-24.

Suggestion · non vérifié

Choose the image carefully and keep the prompt short and close to the image.

Suggestion · non vérifié

To use LoRAs, enable the indicated node.

Suggestion · non vérifié

The description advises against using GPTs with this workflow.

Suggestion

No license is listed for this workflow.