Aller au contenu
WorkflowPrésentéExterne
Ouvrir la source

Daruniawaesf 4K–16K Upscale Context-Tile Generator — V-1.0 Relase Krea2 — V-1.5 Anima

New HR Detail Strength and I2I Input Framing controls, Render Target selection and Tile Compute profiles. Adds adaptive previews and expanded render/PNG metadata; fixes RTX effects at 1x and retains the 16K size...

Sourcecivitai.com/models/2841744
VersionRelease 3366828 — daruniawaesf4K16K_v15Anima.jsonEstimé VRAMNot yet characterized

Profil d'exécution

Accès
Flux de travail externe
Statut
Présenté
Version
daruniawaesf4K16K_v15Anima.json
Source
Civitai
Mis à jour
15 oct. 2026

Description de la source

New HR Detail Strength and I2I Input Framing controls, Render Target selection and Tile Compute profiles. Adds adaptive previews and expanded render/PNG metadata; fixes RTX effects at 1x and retains the 16K size guard. Anima defaults remain 40 steps / CFG 3.5 with the matching Qwen encoder and VAE. Lossless PNG and Classic/Legacy compatibility retained. Includes unpublished V1.2/V1.3 improvements; update the existing custom nodes before use.

What you need

Hardware and download-size estimates are not available yet.

Exigences

Modèles

3

Packs de nœuds

1

Commentaire généré par l’IA

Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.

Objectif

  • This ComfyUI workflow generates images at 4K, 8K, and 16K with staged context-aware diffusion refinement from text prompts or an input image. It provides controls for dimensions, seed, sampler, and pass steps, then saves lossless PNGs with workflow and generation metadata.

Flux

  • High-resolution passes use context-tile diffusion refinement. With 16K Memory Saver on, the workflow refines through 8K before one capped RTX VSR pass reaches 16K.

  • The Anima V-1.5 version adds HR Detail Strength and I2I Input Framing controls, Render Target selection, Tile Compute profiles, adaptive previews, and expanded render and PNG metadata.

Entrées et sorties

  • PNG compression changes file size and encoding time, while the image remains lossless; the front-panel preview is reduced for 8K and 16K images.

  • Generation metadata records the selected checkpoint or Krea2 UNET, HR conditioning mode, refinement profile, sampling configuration, pass settings, and resolution pipeline.

Installation

  • This release uses ComfyUI's Classic/Legacy renderer; ComfyUI Nodes 2.0 beta is not required or recommended.

  • The release notes instruct updating existing custom nodes before use.

Dépendances

  • The Anima version lists anima-base-v1.0.safetensors, qwen_3_06b_base.safetensors, and qwen_image_vae.safetensors.

  • Required custom nodes listed are Context-Anchored Tile Refine, ComfyUI-DaSiWa-Nodes, rgthree-comfy, and ComfyUI-KJNodes.

Configuration

  • To favor composition preservation, try Detail Only HR Conditioning with the Fidelity profile; these are the stated starting choices for that goal.

    Suggestion · non vérifié

  • For systems that cannot process native 16K diffusion, enable Q3 and 16K Memory Saver. For native 16K refinement, enable Q3 and turn Memory Saver off.

    Suggestion · non vérifié

  • SageAttention is optional and off by default; compatibility and performance gains depend on the GPU, PyTorch environment, model architecture, and attention implementation.

Précautions

  • Native 16K processing can require very large amounts of system RAM and VRAM; requirements vary with checkpoint, aspect ratio, tile settings, and model architecture.

  • Semantic drift can still occur when denoise strength, prompt conditioning, or tile refinement settings exceed the selected model's capabilities.

Faut-il modifier cela ?

Connectez-vous pour envoyer une demande de modification.

Sources

1 source
CivitaiPrincipalVersion 3366828
civitai.com/models/2841744

Vérifié 14 oct.

Extraits de sources

1 extrait
Note14 oct.civitai.com/models/2841744

Source context: 464 downloads · Type Workflows · Base model Anima