Encontre o que você precisa para seu fluxo de trabalho.

Qwen Image Workflow — 2512V1

(This is not an exhaustive changelog)

Nabby's SDXL Single/Batch Outpainting to Target Size — Automatic v2.0

Automatic outpaint processing - for each image in batch, up to 4 image streams can be activated to create and automatically save an outpaint.

Silverstar (SD 1.5)

SeedVR2 image upscale

Restore and resize an uploaded image with SeedVR2, producing one output image. For a first run, upload your source image and keep the supplied scale factor of 4, Lanczos resampling, denoise of 1 and color matching set to none. Scale factor multiplies both width and height while preserving aspect ratio. A value of 4 produces roughly sixteen times as many pixels and increases processing demand. Values above 1 enlarge, 1 retains the source dimensions, and values below 1 reduce. Resampling controls interpolation before restoration: Lanczos is the supplied enlargement default, area supports reduction, and nearest-exact retains hard pixel boundaries during resizing. Color matching compares the restored result with the resized source. lab transfers color in CIELAB space; wavelet transfers low-frequency color while retaining generated fine detail; adain matches global per-channel mean and standard deviation. none skips color transfer while retaining geometry alignment. Advanced restoration settings include seed, denoise, steps, guidance scale, sampler and scheduler. Use seed -1 for a fresh random seed each run, or a fixed value to reuse the noise seed. Lower denoise values change the restoration schedule and may retain more source structure. Start with the source baseline of denoise 1, one step, guidance scale 1, Euler sampling and simple scheduling; other sampling configurations are experimental for this tool. Advanced input and output tiling controls separately set spatial encoding and decoding tile sizes and overlaps in pixels. Keep each overlap below its corresponding tile size. The supplied settings are 512-pixel tiles with 128-pixel overlap for both stages. The workflow uses the fixed SeedVR2 7B INT8 model and matching VAE, with conditioning derived from the image rather than an editable text prompt. Generated details may differ from the original; inspect the result when exact fidelity matters.

Flux.2 Klein Photorealism Dual Stage Workflow — v1.0 - T2I

This is a 2-stage workflow which means it starts with the base model at high CFG for strong prompt adherence, then switches to the distilled model (at a specific sigma boundary, around 0.95 works well with 5-6 steps)...

Depth map reference, scene element replacement, style replacement, Flux.2 Klein — v1.0

Depth map reference, scene element replacement, style replacement, Flux.2 Klein. Online trial: Register to receive 1000 RH tokens, enough to process dozens or even hundreds of images. Daily login earns 100 tokens,...

Foton's Workflow with ControlNet upscale — v1.0

Somewhat simple Text to Image workflow with ControlNet tiled upscale

Krea-2 Turbo · Dual-Mode QwenVL Workflow — Keyword Prompt or Image Reference, No Rewiring · + Inline SeedVR2 Upscale — v1.0

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ✨ Krea2 Turbo — QwenVL All-in-One (Auto-VRAM Adaptive) ComfyUI · Krea-2 Community License · Self-Adapting VRAM Engine + Measured Peak-VRAM Proof ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Simple SDXL workflow with upscaling RTX | SVR2 — SVR2 v1.0

initial release

Z Image Turbo Workflow by Stable_Yogi🔥 — ZimageTurbo V2

│ │ └── zimageturbobf16.safetensors and zimageturbo-Q4KS.gguf

XL Matoba Risa/的场梨沙/的場梨沙 Idolmaster/偶像大师

Base Model: Animagine XL V3.1

ZI Yetide Badaki (vrtlYetideBadaki).safetensors

Imagenet Sae Top K 64 Patches Only Layer 4 Hook Resid Post 64 77

This model is a sparse autoencoder trained on CLIP's internal representations.

style-transfer-1_15.safetensors

RedCraft | 红潮2 | 赤佬3 INT8/INT4/FP8 Scaled 加速

terraria-style

Originally posted to HuggingFace by sd-concepts-library terraria style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable...

Qwen3.6 27B GGUF

> [!IMPORTANT] > This model is automatically converted using

Create a HeyGen talking-head video: mechanisms and practical controls

Turn a written script into one talking-head video; choose the speaker, delivery and video shape separately from export settings.

崩坏3立绘/cg风格 Honkai impact 3rd style

Using approximately 120 illustrations/CG images for training, imitating the style of Honkai Impact 3rd, which is similar to tracing 3D models.

[XL][Clothing] Alice-in-Wonderland Outft / 不思議の国のアリス衣装

Please buy me a coffee if you liked my models! Your goodwill will be used for server costs for generating models.