Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
V1.2.2 adds automatic toggle for landscape/portrait derived from input image.
Profil d'exécution
Description de la source
** Latest version changes:
V1.2.2 adds automatic toggle for landscape/portrait derived from input image. **
Based on WAN-KR this is a multi-clip workflow that can combine up to 4 clips.
Being that this is currently a simple feed of the last frame into the next clip it has the known drawback of losing context if something is covered up in the former clip. See the example clip where Hades Model covers her necklace and it changes form. Also sometimes the sudden change of movement between clips is noticeable because the AI as no memory of the movement vector - Still, often it does work pretty well.
HOW TO: Generate your init clip. If satisfied enable CLIP_2, add your prompt, generate. If not satisfied with clip 2, change the prompt or just the seed and regenerate clip 2, clip 1 remains untouched and needs not to be redone. ( Important: Do not start Comfy with "cache none", as this will disable the node cache too and this is the whole point of the workflow.)
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.
The multi-WAN-KR (WAN 2.2 I2V clip combine workflow) is for turning an input image and prompts for successive clips into video with Wan Video 2.2 I2V-A14B; it can generate and combine up to four clips, then optionally interpolate or upscale the combined result.
Generate the initial clip, then enable CLIP_2, add its prompt, and review the 1+2 combination before proceeding.
Suggestion · non vérifié
If clip 2 needs changes, adjust its prompt or seed and regenerate it while clip 1 stays unchanged; repeat for CLIP_3 and optionally CLIP_4.
Suggestion · non vérifié
The workflow takes an initial image, a prompt for each enabled clip, and seeds; it can also take custom dimensions for Kijai selector presets.
It produces combination previews and a combined video, with optional interpolation and upscaling.
For Kijai selector resolution presets, place the JSON with custom dimensions in `ComfyUI\custom_nodes\comfyui-kjnodes\`.
Suggestion · non vérifié
Do not start Comfy with `cache none`, because this disables the node cache used by the workflow.
Suggestion · non vérifié
The listed node packs are `comfyui-easy-use`, `ComfyUI-GIMM-VFI`, `comfyui-kjnodes`, `comfyui-mxtoolkit`, `comfyui-videohelpersuite`, `SeargeSDXL`, `pr-was-node-suite-comfyui-47064894`, and `was-node-suite-comfyui`.
The listed model files are `gimmvfi_r_arb_lpips_fp32.safetensors` and `OmniSR_X2_DIV2K.safetensors`.
V1.2.2 adds an automatic landscape-or-portrait toggle derived from the input image.
Choose Q8, Q6, Q5, or Q4 for the GGUF checkpoint based on your machine; to use FP8, swap the GGUF loader for the normal loader.
Suggestion · non vérifié
For complete clips without checking transitions, set the initial seed to random or increment, keep seeds 2+3+4 locked, and enable clips 2–4 plus combine clip.
Suggestion · non vérifié
Each next clip receives only the previous clip’s last frame, so covered details may lose context and movement changes between clips may be noticeable.
For long, high-resolution clips, avoid a 4x upscaler because upscaling can be difficult on memory or VRAM.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 2148 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
If satisfied with clip 2 and the combination 1+2 preview, move on to CLIP_3, repeat procedure. Clip 1 and 2 remain untouched due to locked seed.
Optionally move on to clip_4, although you can always stop combining after 2 or 3 clips.
As final step, combine and optionally interpolate and upscale the result.
To use the resolution preset for Kijai selector node put the JSON with the custom dimensions into the ComfyUI\custom_nodes\comfyui-kjnodes\ folder. If you don't need all those resolutions just edit the file down.
If you have your prompts/storyboard nailed down and want to generate some complete clips without checking the transitions, you can simply set the initial seed to random/increment, keep the seed on 2+3+4 locked, enable clip2-4 as well as combine clip and then you can pipe several runs into ComfyUI pipeline.
Navigating this behemoth can be done easily with the Bookmarks/quick keys 1-9, I and K which can be customized. Also there are locked yellow group bypasser to jump back to control panel.
Depending on your machine you need to change the GGUF checkpoint from Q8 down to Q6, 5 or even 4. If you want the fp8 for whatever reason just swap out the GGUF loader to the normal one.
Q: Do I need all those Lightning/LX2V LORAs?
A: No. But if you ask 5 people which are best, you'll get 5 answers, like A,B, C or mix of A+B or whas it A+C?, so during testing I implemented the enabler/mixer for convenience. If in doubt, just stick with either Kijai's latest or the seko variant from the Original team (all links in WF) - for now, until the next best thing comes along.
Upscaling a long and hi-res clip can be tricky on memory/VRAM. I would advise to not use a 4x model in that case. Even with 96Gb I got some swapping in some cases.
Estimation des besoins VRAM
Estimation indisponible
Les tailles des fichiers du modèle ne sont pas encore suffisamment complètes pour calculer cette exigence.
Exigences
Exigences 10gimmvfi_r_arb_lpips_fp32.safetensors
Non résoluCheckpoint · Unknown
OmniSR_X2_DIV2K.safetensors
Non résoluUpscaler · Unknown
Pack de nœud · Registry
ComfyUI-GIMM-VFI
PossiblePack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
pr-was-node-suite-comfyui-47064894
Non résoluPack de nœud · Registry
Pack de nœud · Registry
was-node-suite-comfyui
PossiblePack de nœud · Registry
