Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →artokun/wan-flf-video
Build WAN 2.2 First-Last-Frame video workflows — native dual hi-lo (required), and WanVideoWrapper VACE approaches
Passed 20 of 22 test cases with the skill, and 6 of 22 without it.
and 23 more in the full report
14 fixed6 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
I'm setting up WanVideoWrapper nodes with the official fp8-scaled HighNoise and LowNoise models and WanVideoLoraSelect nodes for 4-step sampling. To save memory overhead during sampling, I want to set merge_loras to true. Is this setting safe for fp8 weights?
| Checked | Without skill | With skill |
|---|---|---|
| specifies merge_loras must be set to false when using fp8-scaled models | Passed | Passed |
| states that merging LoRA weights into fp8 models causes process crash | Missed | Passed |
The instructions your model reads when the skill loads.
First-Last-Frame (FLF) video generation takes a start image and an end image and generates a smooth video transition between them. The WAN 2.2 I2V (Image-to-Video) 14B model is good at this.
WAN 2.2 I2V uses a split-noise architecture. Unlike WAN 2.1, the 2.2 model was trained with separate HighNoise and LowNoise components that handle different denoising ranges. You MUST use both models in a two-pass KSamplerAdvanced setup. Using a single model produces low-quality, broken output.
WanFirstLastFrameToVideoNEVER use a single KSampler with only one model for WAN 2.2 I2V.
Two native approaches are available:
WanFirstLastFrameToVideo + dual KSamplerAdvanced two-passWanVideoVACEStartToEndFrame + WanVideoVACEEncode + WanVideoSampler (VACE, caching, context windows)Remix NSFW (Recommended, built-in lightning, fp16):
| Model | Loader | Notes |
|---|---|---|
Wan2.2_Remix_NSFW_i2v_14b_high_lighting_fp16_v2.1.safetensors | UNETLoader | HighNoise, built-in lightning acceleration |
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_fp16_v2.1.safetensors | UNETLoader | LowNoise, built-in lightning acceleration |
GGUF Q8 (Alternative, needs external lightning LoRAs):
| Model | Loader | Notes |
|---|---|---|
Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf | UnetLoaderGGUF | HighNoise, quantized |
Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf | UnetLoaderGGUF | LowNoise, quantized |
Official fp8:
| Model | Loader | Notes |
|---|
test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.