DEV Community

AI-KSK
AI-KSK

Posted on Originally published at huggingface.co

FLUX: Anima Aesthetic Testing — 10 Workflows, Read From the Graphs

FLUX: Anima Aesthetic Testing — 10 Workflows, Read From the Graphs

This release ships 10 workflow files built around FLUX. Together they total 342 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
Anima+Aesthetic+1.1|文生图+CN+修脸+修手+ 60 96 — 512x512 1f
Testing+Anima-Edit+loras+and+IC-methods 52 79 — —
Anima+Aesthetic+1.1|图生图+CN+修脸+修手 52 81 — —
Anima+Aesthetic+1.1|分块放大 45 67 — —
Anima+Aesthetic+1.1|ControlNet精准控制 32 44 — 512x512 1f
Anima+Aesthetic+1.1|三阶高质量渲染 26 43 — 1024x1024 1f
Anima+Aesthetic+1.1|1.5倍放大 20 31 — 1024x1024 1f
Anima+Aesthetic+1.1|DMDX+四步极速版 19 24 — 1024x1024 1f
Anima+Aesthetic+1.1|图生图 19 25 — —
Anima+Aesthetic+1.1|文生图 17 22 — 1024x1024 1f

The node count range is wide: Anima+Aesthetic+1.1|文生图 at 17 nodes against Anima+Aesthetic+1.1|文生图+CN+修脸+修手+ at 60. 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
anima_aestheticV11.safetensors XB_UNetNameBroadcaster
!!!!黑兽超越真实3nsfw.safetensors EnhancedLoadDiffusionModel
qwen_image_HDR_vae_fp32_comfy.safetensors VAELoader
qwen_3_06b_base.safetensors CLIPLoader
Anima-LLLite/anima-lllite-inpainting-v2.safetensors AnimaLLLiteApply
Anima-LLLite/anima-lllite-any-test-like-v2.safetensors AnimaLLLiteApply
anima-base-202605-v1.0.safetensors UNETLoader
4x_NMKD-Siax_200k.pth UpscaleModelLoader
sam_vit_b_01ec64.pth SAMLoader
waiANIMA_v10(anima3).safetensors UNETLoader
Anima-LLLite/anima-lllite-any-test-like-1-step2000.safetensors AnimaLLLiteApply

LoRAs in play

LoRA Weight
lora_edit_ZeroTwo.safetensors 1
AnimaEditV1.safetensors 1
anima-highres-aesthetic-boost.safetensors 1
anima-turbo-lora-v0.2.safetensors 1
dmdx_student_final_comfy.safetensors 1
Gundam_RX78_Flux.safetensors 0.85

Not every LoRA runs at 1.0 — the non-default weights here are [0.85]. 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, 512x512 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

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

  • Anima+Aesthetic+1.1|1.5倍放大
  • Testing+Anima-Edit+loras+and+IC-methods
  • Anima+Aesthetic+1.1|ControlNet精准控制
  • Anima+Aesthetic+1.1|DMDX+四步极速版
  • Anima+Aesthetic+1.1|三阶高质量渲染
  • Anima+Aesthetic+1.1|分块放大
  • Anima+Aesthetic+1.1|图生图+CN+修脸+修手
  • Anima+Aesthetic+1.1|图生图
  • Anima+Aesthetic+1.1|文生图+CN+修脸+修手+
  • Anima+Aesthetic+1.1|文生图

Files

https://huggingface.co/AI-KSK/ksk-video-279-comfyui-workflows

Video walkthrough: https://youtu.be/ShiAjBa8EXc
Bilibili: https://www.bilibili.com/video/BV1xJKB6vEfp/

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)