PipePublicadoAlojado

Capybara image edit

Edit an uploaded image with written instructions using Capybara v0.1 and receive still-image results.

Workflow details

FamiliaHunyuanResolución1024x1024VRAM estimadaNot yet characterizedPublicadorSweet Tea AutomationActualizado27 octBcalidad

Perfil de ejecución

Hover nodes for Pipe controls

Core

Primary Pipe surface

Source image

LoadImage

Input

Edit instructions

CLIPTextEncode

Output size

ResizeImageMaskNode

Extended

Additional surfaced controls

Negative prompt

CLIPTextEncode

Image variants

HunyuanVideo15ImageToVideo

Randomization

RandomNoise

Prompt guidance

CFGGuider

Sampling

BasicScheduler

Sampler

KSamplerSelect

Sampling shift

ModelSamplingSD3

Visual reference

CLIPVisionEncode

Hardware and download-size estimates are not available yet.

Requisitos

byt5_small_glyphxl_fp16.safetensors
No resuelto
Text encoder · Hugging Face · Comfy-Org/HunyuanVideo_1.5_repackaged
capybara_v0.1.safetensors
No resuelto
Checkpoint · Hugging Face · Comfy-Org/HunyuanVideo_1.5_repackaged
hunyuanvideo15_vae_fp16.safetensors
No resuelto
VAE · Hugging Face · Comfy-Org/HunyuanVideo_1.5_repackaged
qwen_2.5_vl_7b.safetensors
Archivo sin verificar
Text encoder · Hugging Face · Comfy-Org/HunyuanImage_2.1_ComfyUI · HunyuanImage 2.1
sigclip_vision_patch14_384.safetensors
No resuelto
Vision model · Hugging Face · Comfy-Org/HunyuanVideo_1.5_repackaged

tea-time-labs/sweet-tea-nodes
Encontrado
Paquete de nodos · GitHub · tea-time-labs/sweet-tea-nodes

Fuentes

1 fuente

Sweet TeaFuente