Add : Change of execution order between interpolation and upscaling, really independent and better optimized.
Profil d'exécution
Description de la source
Bugfix : upscaling node
Add : Change of execution order between interpolation and upscaling, really independent and better optimized.
Remaining hardware or download-size estimates are not available yet.
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.
【WAN2.1】TXT to VIDEO — v1.5 is a ComfyUI workflow for turning text prompts into Wan Video content; it can generate text-to-video and text-to-image results, optionally upscale them, and save images with generation parameters. Its meaningful inputs are a text prompt and the listed
The workflow includes nodes for text encoding, model loading, sampling, VAE decoding, video-frame combining, interpolation, upscaling, and saving.
Version v1.5 changes the execution order of interpolation and upscaling.
The named model files are 4x_foolhardy_Remacri.pth, rife47.pth, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, and wan2.1-t2v-14b-Q3_K_S.gguf.
Saved images can include all generation parameters for online publishing and remixing.
Enable ComfyUI’s Nodes 2.0 (Vue) interface by turning on "Use Nodes V2 (Vue)," refreshing ComfyUI, and then loading the workflow.
Suggestion · non vérifié
Install ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching "UmeAiRT," or use the UmeAiRT Auto-Installer.
Suggestion · non vérifié
Named node packs are: comfyui-custom-scripts; comfyui-easy-use; comfyui-frame-interpolation; comfyui-gguf; comfyui-impact-pack; comfyui-kjnodes; comfyui-mxtoolkit; comfyui-videohelpersuite.
Manual setup lists a T2V model in fp16 or fp8, or a T2V Quant Model in Q8, Q5, or Q3, in models/diffusion_models; umt5_xxl_fp8_e4m3fn_scaled.safetensors in models/clip; wan_2.1_vae.safetensors in models/vae; lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16.safetensors in
Toggle the built-in SeedVR2 tiled upscaler on or off.
Use three LoRA slots with individual on/off controls and strength settings; additional LoRA modules can be connected.
The classic ComfyUI interface may have display problems; enable "Use Nodes V2 (Vue)" and refresh before loading the workflow.
Suggestion · non vérifié
Before use, verify that the page shows "【WAN2.1】TXT to VIDEO — v1.5" from UmeAiRT and that the named model files and node packs are available in your ComfyUI setup; no license is specified.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 15970 downloads · Type Workflows · Base model Wan Video
Exigences
Upscaler · 63.9 MB · PTH · Hugging Face · FacehugmanIII/4x_foolhardy_Remacri
Checkpoint · Hugging Face
Text encoder · 6.27 GB · SAFETENSORS · fp8 · pruned · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
VAE · 242 MB · SAFETENSORS · fp16 · full · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
Checkpoint · 6.51 GB · Hugging Face · UmeAiRT/ComfyUI-Auto_installer
comfyui-custom-scripts
TrouvéPack de nœud · Registry
comfyui-easy-use
TrouvéPack de nœud · Registry
comfyui-frame-interpolation
TrouvéPack de nœud · Registry
comfyui-gguf
Pack de nœud · Registry
comfyui-impact-pack
TrouvéPack de nœud · Registry
Pack de nœud · Registry
comfyui-mxtoolkit
TrouvéPack de nœud · Registry
comfyui-videohelpersuite
TrouvéPack de nœud · Registry