Trouvez ce dont vous avez besoin pour votre flux de travail.

Zoda Anima Workflow — general

( Last Update : 2026-07-03)

Z-Image / Z-Image-Turbo + Lora T2I

Two workspaces for Comfy UI

【FLUX】IMG to IMG — v3.2

Some correction

ZI Andrea Botez (vrtlAndreaBotez).safetensors

ZI Emily Osment (vrtlEmilyOsment).safetensors

Chikage Ootori (Real Eroge Situation! 2 )

Chikage Ootori (Real Eroge Situation! 2 )

PMRF image enhancer

Upload a source image to produce a PMRF-enhanced image. For a first run, keep the source defaults of 2× scale, 25 steps, and Lanczos interpolation. Scale controls enlargement; use 1× to process at the original size. Larger scales increase output dimensions and resource requirements. Steps controls the processing iteration count and trades additional computation for a different restoration result. Interpolation selects the resizing method. Seed lets you vary the result; the default randomizes on each run. This workflow has no prompt or restoration-strength control. Uploaded transparency is not preserved because only the loader's RGB image output is connected.

Melody "Celesty McMarden" Wave - Heroine? Saint? No, I'm an All-Works Maid (And Proud of It)! / メロディ・ウェーブ / Heroine? Seijo? Iie, All Works Maid desu (Hokori)! , ヒロイン?聖女?いいえ、オールワークスメイドです(誇)!

Melody "Celesty McMarden" Wave - Heroine? Saint? No, I'm an All-Works Maid (And Proud of It)! / メロディ・ウェーブ / Heroine? Seijo? Iie, All Works Maid desu (Hokori)! , ヒロイン?聖女?いいえ、オールワークスメイドです(誇)!

Unlearn Cl Ucf101 Videomae Base Random Label 10 42

This model is a fine-tuned version of MCG-NJU/videomae-base on the ucf101 dataset. It achieves the following results on the evaluation set: Loss: 0.8124 Accuracy: 0.7958 Test Accuracy: 0.7958 Df Accuracy: 0.9353...

(pony)kda super fan Neeko League of Legends tft

1girl,solo,torn pants,fingerless gloves,black gloves,multicolored hair,hood,orange eyes,hood down,bangs,cropped hoodie,black pants,navel,blue hair,orange hair,short hair,facial mark,crystal,black hairband,tail,leg...

Use a background-removal mask in an image edit

Extract a separate foreground mask, inspect its alignment and polarity, and decide how an existing edit or composite flow should consume it. Segmentation alone does not preserve original pixels.

ComfyUI_SwapAndScale

Custom ComfyUI node to swap Height and Width input easily. Also you can set both height and width to a 32px scale and limit total to 1MP

comfyui-gender-tag-filter

Filters gendered Danbooru style tags and natural language to a prefered binary gender for automated workflows.

ComfyUI-OpenImage

CustomNode for ComfyUI. It does what it says. Lets you open a generated Image in a specified application after generation.

ComfyUI-VideoSlice

ComfyUI custom node: ib video slicer — MP4/MOV to single IMAGE frame

ComfyUI_MetaSaver

A save node for all the meta data you want!

lora-stacker-civitai-tags

Simple Comfyui plugin to make working with lora stackers easier.

ComfyUI-LoadResizeImageWithFilenameV02

Load & Resize Image node with mask and filename output for ComfyUI

ComfyUI-DiscordWebhookWithInput

Improved the basic Discord webhook node to add the prompt in the send

ComfyUI-ZFL-JSON-Extractor