Loading
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
The workflow allows ultra-fast iterations over different seeds/prompts/images/settings before rendering the final video at full resolution, while removing the need to constantly swap between models (which is ideal...
Profil d'exécution
Description de la source
v2
The workflow allows ultra-fast iterations over different seeds/prompts/images/settings before rendering the final video at full resolution, while removing the need to constantly swap between models (which is ideal for low-RAM setups).
How it works
There are 2 stages:
Generate a draft version of your video at low resolution, using the high-noise model only.
Upscale the video latent to render it at your target resolution, using the low-noise model only.
Process
Stage 1
Commentaire généré par l’IA
Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.
This ComfyUI image-to-video workflow turns an image and prompt into a target-resolution video: it first makes a low-resolution draft with the high-noise model, then upscales the draft’s latent and renders the video with the low-noise model. You can vary seeds, prompts, images, or
For Stage 1, disable LN and Post, add an image and prompt, choose a low-resolution width, and run the high-noise model to create a draft.
For Stage 2, load the draft in ComfyUI, disable HN, enable LN and Post, select the same draft in the Load Draft node, choose a higher width, and run the low-noise model.
The first pass produces a video draft for the second pass to reload, which outputs the video at the target resolution.
The workflow is based on Wan Video 2.2 I2V-A14B.
Install ComfyUI-KJNodes and RES4LYF if missing. ComfyUI-GIMM-VFI is listed as optional for interpolation, and rgthree for fast group bypassing in v2.
The listed required node packs are RES4LYF and ComfyUI-KJNodes (version 1.1.2).
The listed model files include wan2.2_i2v_low_noise_14B_Q5_K_M.gguf, wan_2.1_vae.safetensors, and umt5_xxl_fp8_e4m3fn_scaled.safetensors.
Check whether your setup needs these other named items: wan2.2_i2v_high_noise_14B_Q5_K_M.gguf, Wan_2_2_I2V_A14B_HIGH_lightx2v_4step_lora_v1030_rank_64_bf16.safetensors, wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_1022.safetensors, gimmvfi_r_arb_lpips_fp32.safetensors, or
Suggestion
As a starting point, try a Stage 1 width of 256, 288, or 320 px based on the image aspect ratio, then set Stage 2 to about 2x or 2.5x that width.
Suggestion · non vérifié
For the v1 path, the last sampler should use the beta scheduler; the listed default is linear_quadratic.
Keep video width and height divisible by 16 at both stages; the instructions warn that other dimensions can blur the final output.
Suggestion · non vérifié
Full HD is listed as untested, with 16 GB VRAM posed only as a question; actual hardware needs are unknown.
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
3 extraitsSource context: 2558 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
Disable the groups "LN" and "Post".
Upload your image.
Write your prompt.
Set the low-resolution width (typically, 256, 288 or 320px, depending on the image aspect ratio).
Click "Run".
Stage 2
Drop the video draft created at Stage 1 into the ComfyUI canvas.
Disable the group "HN"; enable the groups "LN" and "Post".
In the "Load Draft" node, select the same video again.
Set the high-resolution width (typically, x2 or x2.5 the width set at stage 1).
Click "Run".
⚠️ Important constraint : make sure the video width and height are multiples of 16 , at both stages of the process, or the final output will be blurred.
The workflow was intentionnally made as simple as possible to maximize compatibility. Up to you to adapt it further to your needs.
For a simpler but less efficient version, see v1 below.
v1
The workflow significantly mitigates the "speed VS quality" dilemma, allowing users with low-end hardware to generate videos in HD resolution nearly twice as fast!
How it works
The principle is dumb simple: we run the high-noise model at very low resolution , then upscale the latent before injecting it into the low-noise sampler.
Since the original image is also reinjected, with a new Wan wrapper node at the low-noise sampling step, visual details are preserved.
Limitations
The motion does lose a little in subtlety, but the speed gain is totally worth it in most of cases.
Not tested on T2V, probably won't work. Works on T2V too. Simply replace both I2V nodes by a EmptyHunyuanLatentVideo node. Thanks to @axicec for sorting this out.
Getting Started
Replace the models by yours, or follow the links below to download them.
Install the required custom nodes listed below if they are missing from your installation.
Load an image and write your prompt.
Click Run .
Speed benchmark
settings : 65 frames, using Q5_K_M I2V models, 4 steps on high-noise with lightx2v 1030, 4 steps on low-noise with lightx2v 1022 and Fun HPS2.1 loras, euler/beta sampler/scheduler on both samplers.
hardware : RTX 3060 with 12GB VRAM and 32GB RAM.
768*1152px (2:3)
768*1152, no upscale: 20′46′′
256*384 x2 then x1.5: 11′16′′ (-46%)
256*384 x1.5 then x2: 10′48′′ (-48%)
720*1280px (9:16)
720*1280, no upscale : 23′19′′
288*512 x2.5 : 15′57′′ (-32%)
288*512 x2 then x1.25: 11′57′′ (-49%) HD : >= 12GB VRAM v
FHD : >= 16GB VRAM ? (not tested, feedbacks appreciated)
Initial sampling resolutions and step settings recommendations are included in the workflow.
Custom Nodes
Required
ComfyUI-KJNodes
RES4LYF
Optional
ComfyUI-GIMM-VFI (for interpolation)
rgthree (for fast group bypassing) (v2)
Models Used
Wan 2.2 14B I2V , Quantized:
Lightx2v LoRas :
Fun LoRa:
Edit (v1) : the last sampler's scheduler is set on linear_quadratic by default but it should be beta .
Remaining hardware or download-size estimates are not available yet.
Exigences
Checkpoint · 75.5 MB · Hugging Face · qazljlj/comfyui2
umt5_xxl_fp8_e4m3fn_scaled.safetensors
Fichier non vérifiéText encoder · Unknown
Source context: 2344 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
Source context: 2264 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
LoRA · 601 MB · SAFETENSOR · Unknown
VAE · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_1022.safetensors
Non résoluLoRA · Unknown
wan2.2_i2v_high_noise_14B_Q5_K_M.gguf
Non résoluCheckpoint · Unknown
Checkpoint · 10.1 GB · GGUF · Unknown
comfyui-gguf
PossiblePack de nœud · Registry
ComfyUI-GIMM-VFI
PossiblePack de nœud · Registry
Pack de nœud · Registry
RES4LYF
TrouvéPack de nœud · Registry
