Animatediff Simple Prompt Traveling — v1.0

Use this workflow to make an AnimateDiff video from different prompts assigned to keyframes; the prompts morph into one another over time.

Set different prompts for keyframes, then generate the video.

Choose between a version for AnimateDiff 2 and 3, or one for AnimateLCM, which is based on AnimateDiff 2.

Both versions are described as including upscaling; the example output is a six-second, 1280 × 720 video made with simple AI upscaling.

This version is listed for the SD 1.5 base model and is v1.0 by Arunderan.

Listed model files include analogMadness_v70.safetensors, AnimateLCM_sd15_t2v.ckpt, AnimateLCM_sd15_t2v_lora.safetensors, RealESRGAN_x2.pth, realismBYSTABLEYOGI_v6LCM .safetensors, rife47.pth, v2_lora_ZoomIn.ckpt, v3_sd15_adapter.ckpt, v3_sd15_mm.ckpt, and vae-ft-mse-840000-ema-<

Named node packs include ComfyUI-AnimateDiff-Evolved (ADE_AnimateDiffLoaderWithContext, ADE_AnimateDiffLoRALoader, ADE_AnimateDiffUniformContextOptions, ADE_ApplyAnimateDiffModelSimple, ADE_LoadAnimateDiffModel, ADE_LoopedUniformContextOptions, ADE_MultivalDynamic, ADE_UseEvolved

Other named nodes include CheckpointLoaderSimple, CLIPSetLastLayer, CLIPTextEncode, EmptyLatentImage, Fast Groups Bypasser (rgthree), Fast Groups Muter (rgthree), FreeU, ImageScale, ImageScaleBy, ImageUpscaleWithModel, KSampler, LoraLoaderModelOnly, RIFE VFI, VAEDecode, VAEEncode

The creator says AnimateDiff and SD 1.5 were trained at 512 pixels and advises against going much higher during generation because results may become inconsistent.

Vorschlag · nicht geprüft

For upscaling, the creator recommends using a separate workflow with a second KSampler.

Vorschlag · nicht geprüft

The creator says the workflows were made with 8 GB of VRAM, reports frequent out-of-memory errors, and recommends at least 12 GB for proper upscaling.

Vorschlag · nicht geprüft

No license information is listed for this workflow.