Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
20 shown of 42,632
Goon's - F2K I2I Edit + SeedVR2 Upscaling — v1.2
Added SeedVR2 upscaling to even further increase output quality without any un-wanted detail loss/adding.
Celestial Bara - Huge Hunk [Illustrious]
A merge of multiple checkpoints to create a style that is hopefully appealing
Ohisashiburi Artist Style
Base model: LTXV 2.3 Trained words:
Anima can edit images! | Testing Anima-Edit loras and IC-methods — Simple Anima IC-method
Just my method for editing images
Z-Image Turbo + (High / Low VRAM) CivitAI metadata + 4k Upscaling + Detail Daemon — v1.0
Simplified version of the Z-Image Turbo + Controlnet (with LoRA fix) + 4k Upscaling + Detail Daemon workflow.
ComfyUI Nunchaku LoRA Patch
The official fix is being tested:
Anima Base 1 Loras
circlestone-labs-non-commercial
Llama 3.2 3b ComfyUI Q8 0 GGUF
This model was converted to GGUF format from WillyChang0806/llama-3.2-3b-ComfyUI using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
Anima 1.0 Base for the PC master race [SFW / NSFW] - Image to prompt + Turbo mode + ControlNet + 4k upscaler + CivitAI medatada — v1.0
Added missing negative prompt and seed to the CivitAI metadata
flux.1-fill-dev-OneReward-int8_convrot
这是一个统一的、目前最先进的图像重绘修复模型,能够高效处理包括图像填充、图像扩展、物体移除和文本渲染在内的多种任务。它超越了包括 Ideogram、Adobe Photoshop 和 FLUX Fill [Pro] 在内的多个领先的商业和开源系统。最后,基于 FLUX Fill [dev],发布了 FLUX.1-Fill-dev-OneReward ,它在图像修复和图像扩展任务中均优于闭源的 FLUX Fill...
Anima ControlNet VACE Depth
circlestone-labs-non-commercial-license
HunyuanDiT v1.2 ControlNet Diffusers Pose
tencent-hunyuan-community
1652753
关于anima模型的相关内容详见官方主页: Anima [官方] - 预览3-基础 |阿尼玛检查站 |Civitai
RMBG 1.4 Wardrobe
bria-rmbg-1.4
Ayu Mog Artist Style
Base model: LTXV 2.3 Trained words:
Andros (Checkpoint) (NoobAI) (AD)
This NoobAI model was made with a combination of two NoobAI models. The idea is to create a model to create realistic model. The reasoning is to have something to make pictures meant to be realistic.
Dinov3 Vits16 Pretrain Lvd1689m ONNX
dinov3-license
Vetehine ┃ Neuron Bankruptcy ANM
moescape.ai is the primary home of this model and a broader collection of additional models. Many of these releases are exclusive to this platform and are not available elsewhere. More information and related work...
LTX 2.3 22b IC LoRA Motion Track Control
ltx-2-community-license
HunyuanDiT v1.2 ControlNet Diffusers Depth
tencent-hunyuan-community
