Skip to content
WorkflowListedExternal
Open source

Combined workflow (ComfyUI txt2img, Wildcards, LLMs/Ollama, Pony, SDXL, Illustrious, Flux, Qwen, Z-Image, Anima, Flux 2 Klein, Krea 2 Turbo) — v8

Added QwenVL as a local LLM (01a, 01b, 01z)

Sourcecivitai.com/models/2149956
TaskMultiCapabilitiesImage to image · Text to image · UpscalingFamilyKrea 2VersionRelease 2756628 — gkr_combined_v8.jsonEstimated VRAMEstimate unavailableDgrade

Runtime profile

Access
External workflow
Status
Listed
Version
gkr_combined_v8.json
Source
Civitai
Updated
Sep 30, 2026

Source description

Added QwenVL as a local LLM (01a, 01b, 01z)

Added QwenVL based "image to prompt" extraction (01c)

Added a new post-positive prompt generation optimization (01z)

Added Detail Deamon for all Samplers and a couple resamplers

Added ZimageBase and Anima

Moved to Sam3 for Detailers detection (removing ultralytics requirements)

Removed requirement to use extra_model_paths.yaml

Rewiring to make use of pipes for cleaner workflow

Added control to VRAM/model offloading (recommended to use Attention with ComfyUI)

Requirements

Models

12

Node packs

19

Sources

1 source
CivitaiSourceVersion 2756628
civitai.com/models/2149956

Verified Sep 30

Source excerpts

2 excerpts
NoteSep 30civitai.com/models/2149956

Source context: 2911 downloads · Type Workflows · Base model Other

NoteSep 28civitai.com/models/2149956

Source context: 2881 downloads · Type Workflows · Base model Other