DEV Community

AI-KSK
AI-KSK

Posted on Originally published at huggingface.co

Qwen Image: VDN NFE Hero Shot — 2 Workflows, Read From the Graphs

Qwen Image: VDN NFE Hero Shot — 2 Workflows, Read From the Graphs

This release ships 2 workflow files built around Qwen Image. Together they total 72 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
H3|VDN 12NFE高质量二采|商品展示 Hero Shot 40 68 — —
Qwen-Image-2.1|商品_主体任意溶图|40步质量 + Viggle加速双路线 32 40 — —

The node count range is wide: Qwen-Image-2.1|商品_主体任意溶图|40步质量 + Viggle加 at 32 nodes against H3|VDN 12NFE高质量二采|商品展示 Hero Shot at 40. 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
minimax_h3_video_vae_fp16.safetensors VAELoader
minimax_h3_audio_vae_fp32.safetensors VAELoader
qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors CLIPLoader
minimax_h3_latent_upscaler_3d_fp16.safetensors MiniMaxH3LearnedLatentUpscaleT8Advanced
minimax_h3_fl_ref_hybrid_scheme_a_25-49_bf16.safetensors UNETLoader
qwen_image_2.1_vae_bf16.safetensors VAELoader
qwen3vl_8b_int8_convrot.safetensors CLIPLoader
qwen_image_2.1_bf16.safetensors UNETLoader
4x-UltraSharpV2.safetensors UpscaleModelLoader
qwen_image_2.1_int8_convrot.safetensors UNETLoader

LoRAs in play

LoRA Weight
Qwenimag21_c2-st2000.safetensors 1
Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r256.safetensors 1

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:

  • H3|VDN 12NFE高质量二采|商品展示 Hero Shot
  • Qwen-Image-2.1|商品_主体任意溶图|40步质量 + Viggle加速双路线

Files

https://huggingface.co/AI-KSK/ksk-video-314-comfyui-workflows

Video walkthrough: https://youtu.be/K6HI-iuMXeg
Bilibili: https://www.bilibili.com/video/BV1AsHy6nEPR/

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)