Bernini-R image editing
Edit an uploaded image with text instructions using Bernini-R. Upload a source image, describe the changes in English and state what should remain unchanged. For a first run, use “make it night,” a 1280-pixel long edge, Turbo enabled, batch size 1 and frame count 1. Run the Pipe to receive an edited image. The resized source supplies the output dimensions and retains the source aspect ratio.
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- Checking published version…
- Updated
- Oct 26, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
Edit instructions
PrimitiveStringMultiline
Output size
ResizeImageMaskNode
Turbo mode
PrimitiveBoolean
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Prompt prefix
CustomCombo
Result count
BerniniConditioning
Randomization
SamplerCustom
Turbo sampling
PrimitiveInt
Turbo stage balance
PrimitiveInt
Turbo guidance
PrimitiveFloat
Standard sampling
PrimitiveInt
Standard stage balance
PrimitiveInt
Standard guidance
PrimitiveFloat
Turbo initial-stage LoRA
LoraLoaderModelOnly
Turbo finishing-stage LoRA
LoraLoaderModelOnly
Sampling method
KSamplerSelect
Noise schedule
BasicScheduler
Finishing-stage noise
SamplerCustom
What you need
Hardware and download-size estimates are not available yet.
Output
- Edited images · image
Requirements
Models
5LoRA · Hugging Face · Kijai/WanVideo_comfy · WanVideo Comfy
umt5_xxl_fp8_e4m3fn_scaled.safetensors
File unverifiedText encoder · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
- File unverified
VAE · Hugging Face · Kijai/WanVideo_comfy · WanVideo Comfy
wan2.2_bernini_r_high_noise_fp8_scaled.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/Bernini-R
wan2.2_bernini_r_low_noise_fp8_scaled.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/Bernini-R
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source