DEV Community

AI-KSK
AI-KSK

Posted on Originally published at huggingface.co

FLUX: image_flux3_klein_image_edit — 7 Workflows, Read From the Graphs

FLUX: image_flux3_klein_image_edit — 7 Workflows, Read From the Graphs

This release ships 7 workflow files built around FLUX. Together they total 106 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
image_flux3_klein_distilled_image_edit 25 27 — 1024x1024 1f
image_flux3_klein_image_edit 25 27 — 1024x1024 1f
07_F07_Base_vs_Distilled_A_B 14 18 — 1024x1024 1f
06_F06_Distilled_BoundingBox_Layout_Edit 13 18 — —
05_F05_Distilled_MultiReference_1to10 12 16 — —
image_flux3_klein_distilled_t2i 9 5 — —
image_flux3_klein_t2i 8 5 — —

The node count range is wide: image_flux3_klein_t2i at 8 nodes against image_flux3_klein_distilled_image_edit at 25. 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
flux3_image_klein_base_int8_convrot.safetensors UNETLoader
qwen3.5_9b_flux3_prompt_upsampler_w4a8.safetensors CLIPLoader

Latent geometry

Distinct latent configurations across the set: 1024x1024 1f.

The frame count matters more than the pixel dimensions here. A graph at 97 frames is built for roughly a four-second unit; one at 121 frames is closer to five. Sigma schedules do not transfer cleanly between them, so treat each geometry as its own tuning target.

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

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

  • 05_F05_Distilled_MultiReference_1to10
  • 06_F06_Distilled_BoundingBox_Layout_Edit
  • 07_F07_Base_vs_Distilled_A_B
  • image_flux3_klein_distilled_image_edit
  • image_flux3_klein_distilled_t2i
  • image_flux3_klein_image_edit
  • image_flux3_klein_t2i

Files

https://huggingface.co/AI-KSK/ksk-video-319-comfyui-workflows

Video walkthrough: https://youtu.be/P2bt83Op9bY
Bilibili: https://www.bilibili.com/video/BV1btJb6LEGS/

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)