Comfy-agent curated_wan_2_2_t2i_14b_gguf_4_step_lora_upscale_insta_portrait

name: curated_wan_2_2_t2i_14b_gguf_4_step_lora_upscale_insta_portrait description: Curated workflow wrapper for Wan 2.2 T2I 14b GGUF + 4 Step Lora + Upscale Insta Portrait.json inputs: prompt: type: string required: false negative_prompt: type: string required: false width: type: integer required: false height: type: integer required: false seed: type: integer required: false steps: type: integer required: false cfg: type: number required: false sampler_name: type: string required: false scheduler: type: string required: false denoise: type: number required: false server: type: string required: false headers: type: object required: false api_prefix: type: string required: false outputs: status: type: string prompt_id: type: string output_images: type: array requirements: models:

• type: diffusion_model name: Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf target_folder: models/diffusion_models
• type: vae name: wan_2.1_vae.safetensors target_folder: models/vae
• type: clip name: umt5_xxl_fp8_e4m3fn_scaled.safetensors target_folder: models/clip custom_nodes:
• ComfyUI-GGUF
• comfyui-kjnodes
• rgthree-comfy links:
• https://discord.com/invite/gggpkVgBf3
• https://huggingface.co/Akumetsu971/SD_Anime_Futuristic_Armor/resolve/main/4x_NMKD-Siax_200k.pth?download=true
• https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors?download=true
• https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors?download=true
• https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/resolve/main/LowNoise/Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf?download=true
• https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main/LowNoise
• https://huggingface.co/lightx2v/Wan2.2-Lightning/resolve/main/Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1.1/low_noise_model.safetensors?download=true
• https://huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1.1
• https://www.youtube.com/@pixaroma
• https://www.youtube.com/watch?v=CgLL5aoEX-s input_modalities:
• text_prompt output_modalities:
• image/png model_families:
• sd3
• wan node_count: 15 node_types:
• CLIPLoader
• CLIPTextEncode
• EmptyHunyuanLatentVideo
• ImageScale
• KSampler
• Label (rgthree)
• MarkdownNote
• ModelSamplingSD3
• Power Lora Loader (rgthree)
• SaveImage
• UnetLoaderGGUF
• VAEDecode
• VAELoader
• WanVideoNAG selection_metadata: family: video_t2v_i2v_avatar resource_profile: very_high complexity_score: 10 estimated_runtime: heavy (can exceed 6 min; best on high-VRAM GPU) warnings:
• Large model(s) detected; ensure enough VRAM and disk space.
• Medium-high resolution detected; expect moderate extra runtime.
• Uses custom nodes; missing nodes can cause validation/runtime failures.
• 'Video workflow: usually slower and VRAM-intensive than still-image workflows.' max_width: 1088 max_height: 1360 max_steps: 8