Loading
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
Finally, a Solution for Consistent Character Posing!
Profil d'exécution
Description de la source
Finally, a Solution for Consistent Character Posing!
Simply input any character you want and the poses you want them to perform, and that's it.
The examples I gave aren't cherry picked. I've tested it like 30 times and they all give me exactly what I asked for.
While waiting for WAN 2.1 to release an image-to-image model with ControlNet support, my workflow is currently the best alternative for achieving consistent character poses .
Better and much faster than Flux Kontext.
On a A4000 gpu with 16GB VRAM, it takes around 40 to 50 seconds to generate 3 images .
Link for the fastest wan2.1 model that I'm using in my 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.
Use this workflow to create images of a character in poses you choose: provide a character and the poses to depict. Its listed base model is Wan Video 14B t2v.
The author says you can use poses from the Openposes Collection or your own.
The page describes an example that produces three images.
Find Dingoo’s workflow on Civitai: https://civitai.com/models/1796490.
The workflow names these model files: umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, and Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE-Q5_K_M.gguf.
The workflow names these ComfyUI node packs: comfyui-inspyrenet-rembg, comfyui-custom-scripts, comfyui_essentials, comfyui-videohelpersuite, comfyui-easy-use, and comfyui-kjnodes.
The workflow also names ComfyUI-GGUF and was-node-suite-comfyui; check which packages these names refer to before installing them.
Suggestion · non vérifié
The author describes using Wan2.1 VACE with 4 steps and 1 cfg.
For another Wan2.1 VACE model, adjust the steps and cfg to what works for that model; the author says the settings may need to be increased.
Suggestion · non vérifié
For Triton, torch, or CUDA errors, the author suggests bypassing the torchcompileModelwanVideoV2 node, choosing “update all” in Comfy Manager, then restarting.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 4846 downloads · Type Workflows · Base model Wan Video 14B t2v
Disclaimer1 : I'm using a very optimized Wan2.1 vace model, if you look at the generation setting, I'm using only 4 steps and 1 cfg. If you want to use your own Wan2.1 vace model , increase those setting with whatever works best for your model. But I highly recommend downloading the one I linked because it's super fast!
Disclaimer2: if you're getting triton/torch/cuda erros, bypass the torchcompileModelwanVideoV2 Node, then "update all" in comfy manager, then restart.
The clip model I'm using : https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors
Poses I used: https://civitai.com/models/22214/openposes-collection (and ofc use your own poses)
Now you can use just one reference image to create a LoRA for your character, or why even bother with a LoRA when you have this workflow?
Hardware and download-size estimates are not available yet.
Exigences
umt5_xxl_fp8_e4m3fn_scaled.safetensors
Fichier non vérifiéText encoder · Unknown
wan_2.1_vae.safetensors
Fichier non vérifiéVAE · Unknown
Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE-Q5_K_M.gguf
Non résoluCheckpoint · Unknown
Pack de nœud · Registry
comfyui-custom-scripts
TrouvéPack de nœud · Registry
comfyui-easy-use
TrouvéPack de nœud · Registry
ComfyUI-GGUF
PossiblePack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
comfyui-videohelpersuite
TrouvéPack de nœud · Registry
was-node-suite-comfyui
PossiblePack de nœud · Registry
