Added model upscaling for much better results
Profil d'exécution
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.
Use Simple Kontext Inpaint Cropping workflow v2.0 with Flux.1 Kontext to make a prompted change to part of an image: start with an image and a mask for the area, then create an edited image.
For best fit, use a LoRA that changes only one small part of the image, as the creator suggests.
Suggestion · non vérifié
To select the area, right-click the Load Image node, choose Open Mask Editor, and mask the part you want to change.
For one of the first 10 v2 downloads, the creator advises downloading it again or replacing the Load Image (from outputs) node with a regular Load Image node.
Node packs listed: comfyui-inpaint-cropandstitch, comfyui-kjnodes, ComfyUI-nunchaku, and rgthree-comfy.
Model files listed: flux1-dev-kontext_fp8_scaled.safetensors, ae.safetensors, t5xxl_fp16.safetensors, clip_l.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors, and RealESRGAN_x4plus.safetensors.
Two other filenames listed are svdq-int4_r32-flux.1-kontext-dev.safetensors and Marksketdra-4bits.safetensors; check whether your setup uses these exact files.
Suggestion · non vérifié
Version v2.0 adds model upscaling for the masked area and includes Nunchaku and non-Nunchaku versions.
The creator suggests placing an upscaler after cropping and before resizing for Flux Kontext; final upscalers mainly make the image larger.
Suggestion · non vérifié
Flux Kontext may change the resolution slightly and leave the final image misaligned with the original, so check alignment after editing.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
2 extraitsSource context: 544 downloads · Type Workflows · Base model Flux.1 Kontext
Exigences
VAE · 320 MB · SAFETENSORS · Hugging Face · Comfy-Org/Lumina_Image_2.0_Repackaged
Text encoder · 235 MB · SAFETENSORS · Hugging Face · comfyanonymous/flux_text_encoders
Marksketdra-4bits.safetensors
Non résoluLoRA · Unknown
Upscaler · SAFETENSORS · Unknown
svdq-int4_r32-flux.1-kontext-dev.safetensors
Non résoluCheckpoint · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Hugging Face · xiaofennuonuo/comfyui
comfyui-inpaint-cropandstitch
TrouvéPack de nœud · Registry
Pack de nœud · Registry
Source context: 531 downloads · Type Workflows · Base model Flux.1 Kontext
Pack de nœud · Registry
rgthree-comfy
TrouvéPack de nœud · Registry