DEV Community

AI-KSK
AI-KSK

Posted on Originally published at huggingface.co

FLUX: MOSS StepLab CharRef — 6 Workflows, Read From the Graphs

FLUX: MOSS StepLab CharRef — 6 Workflows, Read From the Graphs

This release ships 6 workflow files built around FLUX. Together they total 82 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
07_MOSS_StepLab_50_8_4_50·8·4步三档生图 22 27 — 1024x1024 1f
01_MOSS_CharRef_角色参考生图 15 17 — 832x1216 1f
05_MOSS_Beauty_人像美感创作 12 11 — 1024x1024 1f
02_MOSS_MAX_ULTRA_QHD_QHD高清生图 11 10 — 2560x1440 1f
04_MOSS_SFT_Style_Lab_SFT风格实验 11 10 — 1024x1024 1f
06_MOSS_Kromoss_8Step_8步文生图 11 10 — 1024x1024 1f

The node count range is wide: 02_MOSS_MAX_ULTRA_QHD_QHD高清生图 at 11 nodes against 07_MOSS_StepLab_50_8_4_50·8·4步三档生图 at 22. 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
moss_image_base_int8_convrot.safetensors UNETLoader
qwen3.5_9b_bf16.safetensors CLIPLoader
flux2-vae.safetensors VAELoader
moss_image_sft_int8_convrot.safetensors UNETLoader
kromoss_int8_convrot.safetensors UNETLoader

LoRAs in play

LoRA Weight
moss_image_charref_v2.safetensors 1
moss_hires_lora_test_v0.4.safetensors 1
moss_image_sft_lora_rank_256_bf16.safetensors 1.4900000000000002
MOSS-Image-Beauty-LoRA-ComfyUI.safetensors 1
8-steps-dmd2-lora.safetensors 1
moss_image_sft_4step_v2.0.safetensors 1

Not every LoRA runs at 1.0 — the non-default weights here are [1.49]. A weight above 1.0 amplifies the LoRA's effect past what its author trained for; below 1.0 backs it off. Both are deliberate tuning choices, not leftovers.

Latent geometry

Distinct latent configurations across the set: 1024x1024 1f, 2560x1440 1f, 832x1216 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

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

  • 01_MOSS_CharRef_角色参考生图
  • 02_MOSS_MAX_ULTRA_QHD_QHD高清生图
  • 04_MOSS_SFT_Style_Lab_SFT风格实验
  • 05_MOSS_Beauty_人像美感创作
  • 06_MOSS_Kromoss_8Step_8步文生图
  • 07_MOSS_StepLab_50_8_4_50·8·4步三档生图

Files

https://huggingface.co/AI-KSK/ksk-video-326-comfyui-workflows

Video walkthrough: https://youtu.be/bvntROsEru0
Bilibili: https://www.bilibili.com/video/BV1UYnU6qEGK/

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)