A drop-in custom ComfyUI node suite built for video editors, motion designers, and creators to force AI-generated video onto real broadcast and social delivery standards without manual dimension math or messy canvas...

0 stars

Status

AufgelistetD · adoption

ModellCivitai

Kyouko Sakura ( older - dekosuke 18gou fanart LOCON version) - Puella magi madoka magica

Beware! This is only related tangentially to canon Madoka Magica and only if you squint. It is solely trained on dekosuke 18gou doujins.

Sekhmet from Castlevania [IllustriousXL]

Reviews, Hearts, Likes etc. are very appreciated!

Illustrious text to image with optional finishing

Generate an image from text using the fixed waiNSFWIllustrious_v130.safetensors checkpoint, with three optional LoRAs, tiled enlargement and automatic subject detailing. No uploaded image is required; the selected result is the saved image after all enabled stages. For a first run, replace the positive prompt with your subject, composition, lighting and style, review the negative prompt, and keep the 1024 × 1024 base size and sampling defaults. The supplied prompt is an example, including score tags and BREAK; prompt conventions depend on the checkpoint. Seed -1 selects a new random seed each run. Use a fixed seed when comparing settings. Width and Height set the base dimensions before enlargement. The advanced sections contain optional capabilities and their tuning controls. All three LoRA slots start disabled. For each slot you want to use, choose a compatible installed LoRA, enable that slot and set its strength. Slots are independent and can be combined. Upscaling starts disabled. Enable it to enlarge the newly generated image before detailing. The default factor of 2 doubles both dimensions: 1024 × 1024 becomes 2048 × 2048. Upscale denoise controls how much the enlargement may reinterpret the image. Tile controls configure processing and blending; seam correction starts at None, and seam controls apply when a correction mode is selected. Tiled decode is also available. Separate upscale steps, guidance, sampler and scheduler controls retain their source defaults; the supplied evidence does not define override or sentinel behavior, including steps=0 and the Pipeline selections. Prompt cleanup is enabled, but the source does not specify which prompt elements it changes. Subject detailing starts enabled with subject=face and denoise=0.5. It runs after generation and any upscaling. Disable it to keep the image without this additional refinement. The source describes face or body detailing; supported subject names depend on the installed Toolkit. Detail denoise controls how much detected regions may change. Low-level detection, crop, mask and sizing controls remain available, but their exact units and semantics are not documented in the supplied evidence. Keep their source defaults for a first run, especially the unusual numeric noise_mask, boolean guide_size and bbox_threshold=1024 fields. Optional-stage controls matter only when their stage is enabled. The checkpoint and baked VAE are fixed; CLIP skip remains adjustable. This Pipe always generates an image upstream and does not accept an existing image for standalone upscaling or detailing. The runtime requires ComfyUI-UmeAiRT-Toolkit and waiNSFWIllustrious_v130.safetensors. The optional upscaler uses 4x_NMKD-Siax_200k.pth; optional LoRAs must also be installed. The source says subject detailing uses detector and segmentation resources downloaded automatically by the Toolkit. Resource inventory currently marks the Toolkit, checkpoint and upscaler unresolved, and the supplied evidence does not verify those automatic downloads.

UpscalingIllustrious1024x10248GB VRAM

Status

AufgelistetUnrated

AnleitungSweet Tea