Added SeedVR2 upscaling to even further increase output quality without any un-wanted detail loss/adding.
Runtime profile
Source description
Added SeedVR2 upscaling to even further increase output quality without any un-wanted detail loss/adding.
change from default model to " Moody Desire Mix - V2.0 EDIT + HEADSWAP " from @catlover1937 for MUCH better nsfw support/quality.
re-seperated image loading nodes that were previously packed into subgraphs with image loaders to ensure using maskeditor on the load image node is still possible.
runs much easier on lower hardware (12gb+ vram reccomended)
Estimated VRAM requirement
Estimate unavailable
19.8 GB across 3 of 5 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use Goon's - F2K I2I Edit + SeedVR2 Upscaling for Flux.2 Klein 9B image-to-image editing: provide a source image and text prompt, then produce an edited image with SeedVR2 upscaling and detail preservation.
The workflow includes image loading, text encoding, sampling, resizing, SeedVR2 upscaling, image comparison, and image saving.
Its inputs are a source image and text prompt; its described output is an edited image with SeedVR2 upscaling.
LoadImage and SaveImage nodes are included for loading the image and saving the result.
The description recommends 12GB or more of VRAM; lower-VRAM setups may still work depending on resolution and settings.
The named node packs are comfyui_essentials, comfyui-easy-use, comfyui-kjnodes, rgthree-comfy, and seedvr2_videoupscaler.
The named model files are ae.safetensors, ema_vae_fp16.safetensors, flux2-vae.safetensors, moodyDesireMix_v20EDITHEADSWAP.safetensors, qwen_3_8b_fp8mixed.safetensors, seedvr2_ema_7b_fp16.safetensors, and z_image_turbo_bf16.safetensors.
The base model is Flux.2 Klein 9B.
SeedVR2 upscaling is integrated, and separated image-loading nodes are described as compatible with Mask Editor on LoadImage.
The description says the default model was changed to Moody Desire Mix - V2.0 EDIT + HEADSWAP.
Before using it, verify that moodyDesireMix_v20EDITHEADSWAP.safetensors and seedvr2_ema_7b_fp16.safetensors are available under those exact filenames.
Suggestion · not verified
License information is not provided.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource context: 425 downloads · Type Workflows · Base model Flux.2 Klein 9B
Requirements
10 requirementsVAE · 320 MB · Hugging Face · Comfy-Org/z_image_turbo
ema_vae_fp16.safetensors
Not resolvedVAE · Unknown
Text encoder · 8.07 GB · SAFETENSORS · fp16 · Civitai · 2617655
seedvr2_ema_7b_fp16.safetensors
Not resolvedCheckpoint · Unknown
Checkpoint · 11.5 GB · Hugging Face · Comfy-Org/z_image_turbo
Node pack · Registry
Node pack · Registry
Source context: 309 downloads · Type Workflows · Base model Flux.2 Klein 9B
Source context: 308 downloads · Type Workflows · Base model Flux.2 Klein 9B
Node pack · Registry
Node pack · Registry
Node pack · Registry