DEV Community

AI-KSK
AI-KSK

Posted on Originally published at huggingface.co

Qwen Image: Krea Identity Edit v1.2 — 3 Workflows, Read From the Graphs

Qwen Image: Krea Identity Edit v1.2 — 3 Workflows, Read From the Graphs

This release ships 3 workflow files built around Qwen Image. Together they total 68 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
单图编辑+(+Krea+2+Identity+Edit+v1.2+) 24 26 — 1024x1024 1f
单图遮罩编辑+(Krea+2+Identity+Edit+v1.2) 22 27 — 1536x1536 1f
双图编辑+(+Krea+2+Identity+Edit+v1.2+ 22 31 — 1024x1024 1f

The node count range is wide: 单图遮罩编辑+(Krea+2+Identity+Edit+v1.2) at 22 nodes against 单图编辑+(+Krea+2+Identity+Edit+v1.2+) at 24. 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
qwen3vl_4b_fp8_scaled.safetensors CLIPLoader
krea2_turbo_fp8_scaled.safetensors UNETLoader
qwen_image_HDR_vae_fp32_comfy.safetensors VAELoader

LoRAs in play

LoRA Weight
krea2_identity_edit_v1_2_fp16.safetensors 1

Latent geometry

Distinct latent configurations across the set: 1024x1024 1f, 1536x1536 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

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

  • 单图编辑+(+Krea+2+Identity+Edit+v1.2+)
  • 单图遮罩编辑+(Krea+2+Identity+Edit+v1.2)
  • 双图编辑+(+Krea+2+Identity+Edit+v1.2+

Files

https://huggingface.co/AI-KSK/ksk-video-282-comfyui-workflows

Video walkthrough: https://youtu.be/CU1UKxjWBRo
Bilibili: https://www.bilibili.com/video/BV1bJgy6eEei/

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)