DEV Community

AI-KSK
AI-KSK

Posted on Originally published at huggingface.co

FLUX: FLUX3 Klein GGUF dchuk — 3 Workflows, Read From the Graphs

FLUX: FLUX3 Klein GGUF dchuk — 3 Workflows, Read From the Graphs

This release ships 3 workflow files built around FLUX. Together they total 52 nodes. Rather than summarise the video, this write-up reads the graphs directly — what each one loads, how big its latents are, and which sampler it runs.

The workflows at a glance

Workflow Nodes Links Sampler Latent
03_FLUX3_Klein_4K_本地文件夹批量_GGUF视觉反推_dchuk_V23_重 19 26 — —
02_FLUX3_Klein_4K_RunningHub_线上ZIP全自动批量_最终版 17 22 — —
01_FLUX3_Klein_4K_单图_RH_LLM自动细节增强_最终版 16 20 — —

The node count range is wide: 01_FLUX3_Klein_4K_单图_RH_LLM自动细节增强_最终版 at 16 nodes against 03_FLUX3_Klein_4K_本地文件夹批量_GGUF视觉反推_dchuk at 19. That gap is usually the difference between a single-pass preview graph and one that adds conditioning, upscale stages, or a second sampling pass.

What the graphs load

Model file Loader node
flux3_image_klein_sd_int8_convrot.safetensors UNETLoader
qwen3vl_4b_int8_convrot.safetensors CLIPLoader
flux2-vae.safetensors VAELoader
RealESRGAN_x4plus.pth UpscaleModelLoader
Huihui-Qwen3.8-27B-abliterated-Q4_K.gguf llama_cpp_model_loader

Where this set is weak

  1. Node count is not quality. The largest graph is not automatically the best one; a 40-node graph with a good prompt beats a 200-node graph with a bad one.
  2. No measured comparison in the files. The workflows carry settings, not benchmarks. Any quality claim needs your own A/B run.
  3. Model files are not included. You supply the weights; the graphs only reference filenames.
  4. Version drift. A graph pinned to a specific checkpoint revision will run on a newer one but may produce different output.

Practical order

Open the smallest graph first. It has the fewest moving parts and will confirm your models load before you spend time on the elaborate ones.

Workflows

2 graphs published on RunningHub with invite code rh-v1111:

  • 01_FLUX3_Klein_4K_单图_RH_LLM自动细节增强_最终版
  • 02_FLUX3_Klein_4K_RunningHub_线上ZIP全自动批量_最终版
  • 03_FLUX3_Klein_4K_本地文件夹批量_GGUF视觉反推_dchuk_V23_重建版

Files

https://huggingface.co/AI-KSK/ksk-video-320-comfyui-workflows

Video walkthrough: https://youtu.be/949qxjckUyI
Bilibili: https://www.bilibili.com/video/BV11xJo6nEFh/

Notes

  • Workflow files only. Model weights are not included and each keeps its own licence.
  • Node counts, geometries and loader filenames above are read from the published JSON files.
  • Independent AI-KSK release. Not affiliated with the model authors or RunningHub.

Optional API platform - 88API (affiliate link)

Explore 88API for access to multiple AI model APIs. Available models, routes and prices are listed on the platform; Alipay top-ups are supported.

https://88api.ai/sign-up?aff=usx3

Disclosure: I may earn a commission from eligible purchases after you register through this referral link.

Top comments (0)