Sign up free, get 10,000 credits

Starter credits added when you sign up.

Sign up and create 8 images for free

Starter credits added when you sign up.

Community DiT

Anima Delta Mix 3.8B Qwen 0.6B

Anima Delta Mix 3.8B Qwen 0.6B - AI Model cover image

Sign up free, get 10,000 credits

Starter credits added when you sign up.

Sign up and create 8 images for free

Starter credits added when you sign up.

Subido en
3 nov 2026, 0:39
Usos
28
Reseñas
Sin reseñas
Pasos de muestreo

40

Escala CFG

4.5

Excluir de la imagen

worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia, signature, artist name, bad hands, fused hands,

Permisos
  • Permitir la generación y el intercambio de imágenes
  • Permitir que los usuarios descarguen este modelo
  • Usos comerciales

Descripción

IMPORTANT. Read this first.This checkpoint is not built for Qwen3.5-4B and not for the expanded adapter.52-block DiT, but text conditioning is native qwen_3_06b_base only.Insert blocks after the frozen 28-stem were prepared for that CLIP. Qwen3.5 will look like stock Pro52, not this mix.Do not use qwen35_4b or Anima-3.8B-expanded_adapter.Delta MixCheckpoint merge on Anima-3.8B (52-block). Anime and illustration first, with extra room for kemonomimi / light furry. Use it like a normal Anima model.Text encoder: qwen_3_06b (native Anima CLIP). Do not swap in Qwen3.5-4B or an expanded adapter.VAE: official Anima / Qwen-Image VAE.PromptPositive starter: anime, masterpiece, best quality, ultra detailed, absurdres, sharp focus, intricate details, cinematic dramatic lighting, strong chiaroscuro,Then the scene in tags or natural language, Anima-style. Rating tag if you use one (safe / sensitive / explicit).RecommendedSteps: 30-40CFG: 4.0–5.5Sampler: Euler ancestral/dpmpp_2mScheduler: normal/sgm_uniformResolution: same as Anima-3.8B (1024-class and up, as VRAM allows).Anima 52 LoRA Patch only for v1https://github.com/bestluner-create/ComfyUI-Anima52-LoRAPatchAnima 52 LoRA Patch for v2+https://github.com/bestluner-create/ComfyUI-Anima-Delta-Q35-LoRA.gitStart around 0.65. Do not stack stock Load LoRA on the same old LoRA.v2Current version on this page.This mix uses: Anima-3.8B Anima Aesthetic 2B Aura Rising aniMurr v02Same text encoder and VAE as v1.0. File: animaDeltaMix38B_v20.safetensorsv3New bake on the same 52-block 0.6B chassisBoth Gen-1 and Gen-2 use copy-body (adaLN stays on the chassis)Denser materials and small surface detail vs v2Same 2B donors — last styled bake on this pairV4Custom models are used for both generations, including the stem. This specific model focuses on delivering a high-quality output with maximum detail and fidelity. I hope you enjoy it.V5/V6/V7/V8Used custom donors / DoraCreditsAnima Base / Anima-3.8B — original authorsMethod: Anima Delta Mix — 2B into 2.9B / 3.8BLicense follows Anima (non-commercial). Do not sell the weights.

Comentarios

Obra de arte hecha por Anima Delta Mix 3.8B Qwen 0.6B