20 shown - 222 total matches
<p>We are pleased to launch version 2.4. This version has epic improvements in visual performance, but it also comes with a side effect: missing fingers.</p>
WAN 2.2 / SVI Pro 2 / I2V for 12GB VRAM V2.1 - small fix, I accidentally removed the required SVI Low LoRa in Stage 2. Obviously an easy fix but fo...
Note: I spend a lot of time on these to make sure they are top notch. If you have ANY issues, I'm very responsive. hit me up and I'll resolve them ...
This is a very simple workflow that helps you to save your HiDream 01 Text to Image Generation Data into a human readable .txt file. This will auto...
<p>Yes really, SD 1.5. Nobody asked for it but you're getting it anyway. I initially did this as a joke but it's surprisingly still somewhat usable in 2026. I applied all the dataset images I created in Z-Image and Big ASP 2.5 to train this model and I think it definitely has some improvements in color and lighting over regular SD 1.5.</p><p>It's just a fun little model that is stupid fast. I don't expect it to be used by anybody for anything but I had fun creating it nonetheless.</p><p>Use the workflow embedded in any of the showcase images for best results.</p><p>Recommended settings:</p><p>Sampler: LCM</p><p>Scheduler: karras, beta, exponential</p><p>Steps: 8-16</p><p>CFG: 1.0-1.5</p>
Source context: 36 downloads · Type Checkpoint · Base model SD 1.5 LCM
✨ WAN2.1 — Image to video — Simple Workflow A clean, all-in-one WAN image-to-video workflow built entirely with the UmeAiRT Toolkit for ComfyUI. On...
Workflow for Anima Any feedback would be appreciated. Downloads official HF repo: https://huggingface.co/circlestone-labs/Anima civitai model page:...
<p><strong>V6.5 is here — and you all helped build it.</strong></p><p>Real thank-you to everyone who pushed V6 hard, <a target="_blank" rel="ugc" href="https://studio.brandulate.com">sent feedback</a>, and posted the broken hands. V6.5's fix list literally came from you. Anatomy, hand grips, expressions, twin-tails, full-body proportions, isolated objects, painterly style separation, hair color consistency — all worked on this round.</p><p><strong>This Post</strong></p><p>If you have 12 GB+ VRAM, these are the files you want.</p><p>FP32 (safetensors, around 13 GB) — Maximum precision. Research and production work. 24 GB+ cards.</p><p>FP16 (safetensors, around 6.5 GB) — The default. Best quality and speed balance for most users.</p><p>BF16 (safetensors, around 6.5 GB) — Same size as FP16, slightly faster on RTX 3000+ with native BF16 support.</p><p>FP8 Scaled (safetensors, around 3.2 GB) — Near-FP16 quality at half the VRAM. Native in Forge and ComfyUI. Great for 8 GB cards.</p><p>All are standard safetensors files. Drop into your checkpoints folder, load from the dropdown.</p><p><strong>Trigger Word</strong></p><p>99rbsy99 — add this to every prompt for the V6.5 realism style. Place it at the END of your tag list for soft activation, or earlier for stronger effect.</p><p>Compatible with my character LoRAs (which use 99bsy99) — they stack cleanly without conflict.</p><p><strong>Recommended Settings</strong></p><p>Sampler — DPM++ 2M Karras, Euler a, or Restart<br />Steps — 25 to 30<br />CFG — 4 to 7<br />Resolution — Native SDXL (1024×1024 or aspect-ratio buckets)</p><p><s...
<p>Join The Tinkerer on <a target="_blank" rel="ugc" href="https://whop.com/joined/cyberdelia-ai-lab/products/the-tinkerer/">Whop</a> to download this model and many more — all for one monthly payment. Plus, get early releases, private tools <strong>and</strong> a lot more.<br />👉 <a target="_blank" rel="ugc" href="https://whop.com/joined/cyberdelia-ai-lab/products/the-tinkerer/">Join on Whop</a></p><p>V5 refines what V4.0 started. Better details, sharper colours, more consistent output, and stronger NSFW content across the board.</p><p>This release adds 110+ new sample images, covering a wider range of styles and scenarios. All images were generated with the <strong>Cyber Z-Image Turbo Workflow v4.1</strong>, available in the Optional Files section.</p>
<p>Join The Tinkerer on <a target="_blank" rel="ugc" href="https://whop.com/joined/cyberdelia-ai-lab/products/the-tinkerer/">Whop</a> to download this model and many more — all for one monthly payment. Plus, get early releases, private tools <strong>and</strong> a lot more.<br />👉 <a target="_blank" rel="ugc" href="https://whop.com/joined/cyberdelia-ai-lab/products/the-tinkerer/">Join on Whop</a><br /><br />This version pushes further away from the Semi-Real branch and offers a more distinct, refined anime-focused experience.</p><p>V5 is a real pleasure to work with. A lot of improvements, fixes, and refinements went in since V4, and the output is much more stable and consistent now.</p><p>I've been working on this version for a while. It actually started back around V3, with steady iteration and fine-tuning over the past month.</p><p>At this point, this is my personal favorite checkpoint.<br /><br />All examples are <strong>100% LoRA-free</strong> and generated with Forge Neo.</p><p>If your results aren’t quite what you expected, take a quick step back and check a few things first:<br />– Did I stack a bunch of LoRAs?<br />– Am I using a lot of Textual Inversions?<br />– Is my prompt actually structured well?</p><p>In most cases, it’s not the checkpoint causing the issue 🙂</p>
✨ WAN2.2 — Image to video — Simple Workflow A clean, all-in-one WAN image-to-video workflow built entirely with the UmeAiRT Toolkit for ComfyUI. On...
✨ FLUX — ControlNet — Simple Workflow A clean, all-in-one FLUX image-to-image ControlNet workflow built entirely with the UmeAiRT Toolkit for Comfy...
Create
This is an advanced workflow for those who want to dail in an image at pro level grade. A simple version can be found HERE Note: I spend a lot of t...
✨ WAN2.1 — Text to video — Simple Workflow A clean, all-in-one WAN text-to-video workflow built entirely with the UmeAiRT Toolkit for ComfyUI. Only...
Create
✨ WAN2.1 — StartEndFrames — Simple Workflow A clean, all-in-one WAN image-to-video workflow built entirely with the UmeAiRT Toolkit for ComfyUI. On...
✨ Z-IMG — Inpaint — Simple Workflow A clean, all-in-one Z-IMG inpaint workflow built entirely with the UmeAiRT Toolkit for ComfyUI. Only 8 nodes . ...
Model repo on Hugging Face Hub.
Red Craft & DarkBeast workflows collection [ NEW ] ideogram 4 06/04 /2026 Ideogram 4 is Ideogram's first open-source text-to-image model. It is...
✨ QWEN — Text to Image — Simple Workflow A clean, all-in-one QWEN text-to-image workflow built entirely with the UmeAiRT Toolkit for ComfyUI. Only ...
✨ Z-IMG — Image to Image — Simple Workflow A clean, all-in-one Z-IMG image-to-image workflow built entirely with the UmeAiRT Toolkit for ComfyUI. O...
