š¢ Muse by Stable Yogi Ā· Krea 2 V3.0 ā Extended and Extended Edit
Two upgraded cuts of Muse V3.0, and both are free for the community.
Same Muse look you know, now with more room to work: run more steps, push the guidance a little, and edit your images right inside the model.
## What's in the pack
š Get the free Extended versions ā HERE
No cost, just the code. Drop a ā¤ļø and tag me if you make something you love.
š£ Extended (Turbo)
The full Muse V3.0 look with the brakes off. The standard turbo model is tuned for quick 8 step images at CFG 1. Extended opens that up so you can slow down for a cleaner, richer result and give the prompt more pull.
š£ Extended Edit
Everything in Extended, plus image editing built in. Give it a picture and a plain instruction: swap an outfit, change a face or hair, add or remove someone, extend the frame, fill a gap, or try on a different look. It keeps the person looking like themselves.
## Settings (both cuts)
- Steps 8 to 20 (16 is the sweet spot) Ā· CFG 1 to 3 (try 2) Ā· Euler Ā· Simple.
- Keep CFG at 3 or below. Higher pushes it too hard and the image starts to break.
- Extended Edit runs with the comfyui-krea2edit node pack. The editing is baked in, so skip the separate edit LoRA loader.
- Model only. Pair with the Qwen3-VL text encoder + Qwen image VAE, same as base Krea 2.
## š How to get it (free)
Both cuts are free with coupon *EXTENDED-MV3** at checkout.
Editing is powered by the Krea 2 Identity Edit LoRA by conradlocke (Krea 2 Community License). Thanks to them.
===========================================================
š¢ Muse by Stable Yogi Ā· Krea2 Ā· V3.0
The next step for Muse ā the editorial look you know, now with more striking presence.
⨠What's NEW in V3.0
- Everything from V2.5, elevated. The full Muse blend plus a more striking, magazine-grade edge.
- Standout faces. Editorial beauty, believable and polished ā holds shot to shot.
- Glossy, cinematic light. Dimensional, produced, that Muse signature.
- Handles anyone. Young to mature, exactly as prompted.
ā Want more? The PRO version pushes presence and depth further ā see below.
Made by Stable Yogi š§ ā drop a ā¤ļø if Muse is your look.
Muse by Stable Yogi Ā· Krea2 Ā· V2.5 NVFP4
MuseĀ byĀ StableĀ YogiĀ Ā·Ā Krea2Ā Ā·Ā V2.5Ā āĀ NVFP4
TheĀ NVFP4Ā (4-bit) build of Realism V1.0 ā made forĀ RTX 50-series / BlackwellĀ cards.
Smallest & fastestĀ ā ~8 GB, native FP4 tensor cores. Lowest VRAM, top speed on 50-series.
Same realismĀ ā real skin, natural light, true-to-life ā no quality loss from 4-bit.
Runs in ComfyUI + the latest ForgeĀ (Blackwell only ā on older cards use the INT8 / fp8 / GGUF versions instead).
āļø Settings:Ā 8 steps Ā· CFG 1 Ā· Euler Ā· Simple Ā· native 1024²+
(Model only ā pair with the Qwen3-VL text encoder + Qwen-Image VAE, same as base Krea 2.)
Made by Stable Yogi , get Pro release on my portal.
Muse by Stable Yogi Ā· Krea2 Ā· V2.5 EXTENDED
š¢ MUSE V2.5 EXTENDED
YourĀ settings,Ā yourĀ lookĀ āĀ MuseĀ V2.5Ā withĀ roomĀ toĀ move.
Most turbo models pin you to one setting: change the steps or the guidance and the image falls apart.Ā Extended doesn't.Ā ItĀ holdsĀ togetherĀ acrossĀ aĀ realĀ workingĀ range,Ā soĀ youĀ canĀ tuneĀ theĀ resultĀ insteadĀ ofĀ acceptingĀ it.
āļø Settings
Recommended: 16 steps · CFG 2 · Euler · Simple · native 1024²+
Works across: 8ā20 steps Ā· CFG 1ā3
ā ļøĀ Don't go above CFG 3.
⨠Why you'd want it
Dial in your own look.Ā Lower CFG for soft and natural, higher for punch and contrast. Fewer steps for speed, more for polish. Your call, not the model's.
Extra steps actually pay off.Ā At 16 steps you get the richest version of Muse ā deeper light, warmer tone, more presence.
It follows your prompt harder.Ā More guidance headroom means when you ask for a specific scene, you get that scene.
Still quick when you're in a hurry.Ā 8Ā stepsĀ worksĀ fineĀ forĀ draftsĀ andĀ batchĀ runs.
šÆĀ WhichĀ oneĀ shouldĀ IĀ use?
BestĀ for Muse V2.5Ā (standard)Speed.Ā SharpestĀ atĀ 8Ā stepsĀ āĀ theĀ everydayĀ default.
Muse V2.5 Extended
ControlĀ andĀ qualityĀ ceiling.Ā GiveĀ itĀ 16Ā steps,Ā CFGĀ 2.
š¦ DownloadĀ āĀ INT8-ConvRotĀ (fast INT8 tensor cores, loads natively in Forge + ComfyUI,
MadeĀ byĀ StableĀ YogiĀ š§Ā āĀ dropĀ aĀ ā¤ļøĀ andĀ showĀ meĀ whatĀ youĀ tuneĀ itĀ to. Looking for a Pro Version check here on my portal.
=========================================================
Muse by Stable Yogi Ā· Krea 2 Ā· V2.5
The full-spectrum edition of Muse on Krea 2 ā same photoreal turbo, a wider, richer blend.
⨠What's NEW in V2.5
- A broader, more varied blend ā more range across faces, skin, and lighting moods.
- True photorealism ā real skin texture, pores, freckles, natural light (not AI-glossy).
- Believable faces, consistent ā holds up shot to shot.
- Turbo ā full images in 8 steps.
š§ V2.0 vs V2.5
- Companion release to V2.0 ā we put out both so you can pick your favourite. V2.0 is the tighter, more focused cut; V2.5 is the fuller blend with a touch more variety. Same engine, same speed.
š¦ Downloads
- INT8-ConvRot ā fast (INT8 tensor cores), loads natively in Forge + ComfyUI.
- Q8 GGUF ā near-lossless. Ā· Q4 GGUF ā low VRAM / small download.
- (Model only ā load the *Qwen3-VL text encoder + Qwen-Image VAE** alongside, same as base Krea 2; they auto-download.)*
āļø Settings
- 8 steps Ā· CFG 1 Ā· Euler Ā· Simple Ā· native 1024ā2048.
ā Want more punch? Grab the PRO edition from my portal, dials detail and depth up further.
Made by Stable Yogi ā drop a ā¤ļø and tell us: V2.0 or V2.5?
=========================================================
Muse by Stable Yogi ā Krea2 Ā· V2.0 EDIT (INT8)
For details of this release, please read the "About this model" section
==========================================================
Muse by Stable Yogi Ā· Krea2 Ā· V2.0 (INT8)
The next evolution of Muse on Krea 2 ā more real, more detailed, same turbo speed.
⨠What's NEW in V2.0
A real jump in photorealismĀ ā skin now has genuine texture: pores, freckles, fine detail (less "AI-smooth").
Shot-on-camera lookĀ ā believable faces, natural lived-in complexion.
Richer, more dimensional lightingĀ ā window light, soft shadows, real depth.
Holds up across promptsĀ ā lifelike skin and faces, consistent shot to shot.
š§ What CHANGED (vs V1.5)
Built on the V1.5 engine, evolved with fresh photoreal character detail.
Cleaner, more natural rendering ā over-polished feel gone.
StillĀ turboĀ ā full images inĀ 8 steps.
š¦ DownloadsĀ āĀ INT8-ConvRotĀ (Forge + ComfyUI native) Ā·Ā Q4 GGUFĀ (low VRAM).Ā (Load Qwen3-VL TE + Qwen-Image VAE alongside ā auto-download.)
āļø SettingsĀ āĀ 8 steps Ā· CFG 1 Ā· Euler Ā· Simple Ā· native 1024ā2048.
āĀ PRO edition on my portal dials it up further.
===========================================================
Muse by Stable Yogi ā Krea 2 Ā· V1.5
Photoreal Krea 2 ā fast, versatile, built to look genuinely real.
⨠What it is
Photorealistic model onĀ Krea 2, tuned by Stable Yogi Ā·Ā turbo (8 steps)Ā Ā· plug-and-play with the Krea 2 TE + VAE.
šÆ Great for
PhotorealĀ portraitsĀ &Ā full-body
Any character
Fashion & editorialĀ
Lifestyle & scenesĀ
better lighting
Strong prompt-followingĀ
Natural skin & facesĀ
š¦ DownloadsĀ āĀ Q8 GGUF (recommended)Ā Ā·Ā Q4 GGUF (low VRAM)Ā Ā·Ā fp8 (compat)Ā (load TE + VAE alongside)
āļøĀ 8 steps Ā· CFG 1 Ā· Euler Ā· Simple Ā· native res
āĀ Want more punch? TheĀ PROĀ edition on my portal is dialed up further.
===========================================================
Muse by Stable Yogi ā Krea 2 Ā· V1 Experimental
A photorealistic model onĀ Krea 2, tuned for lifelike portraits, natural skin & light ā at turbo speed.Ā V1 Experimental: an early release, feedback welcome.
⨠Photoreal portraits & characters · 8-step turbo · native high-res · versatile (portrait / editorial / lifestyle / concept) · plug-and-play (TE + VAE built in).
āļøĀ 8 steps Ā· CFG 1 Ā· Euler Ā· Simple Ā· native 1024ā2048.
š¦ Fp8 (full quality) Ā· Q8_0 / Q4_0 GGUF (low-VRAM).
Looking for a Pro version get it free at my portal
Drop a ā¤ļø and share your creations.
To run this model on Forge UI, look here https://civarchive.com/articles/32010/run-krea-2-in-forge-free-extension-first-on-forge
Description
Experimental Build with some spice.
Looking for a Pro version get it free at stable yogi
FAQ
Comments (29)
LOL how did you manage to INCREASE the size of a model by training it. This is like 50% larger than Krea 2 fp8...
Because its not a fine-tune or what you would normally consider to be a "trained model", most of the "trained models" are barely trained, with a bunch of Loras baked in
@willywizardĀ That isn't how checkpoint training works. You could train it with a ton more data and not increase the size of the model. We aren't increasing the parameters with normal training.
The fp8 is a completeĀ all-in-oneĀ ā it packs the full image model, the prompt text-encoder, and the VAE into one file withĀ zero wasted space, so you just load it and generate, nothing else to download. That's genuinely why it's ~20 GB. If you want a smaller download, theĀ Q8 GGUFĀ is leaner and actually a touch sharper ā you load the text encoder + VAE alongside it.
@Stable_YogiĀ Oh... Eww, Okay yeah I didn't see that it said "AIO" lmao
@Stable_YogiĀ Correct me if i'm wrong but for most of these more advanced models we have to load the text encoder and vae seperately anyway. So if we have a workflow already set up for that, why the all in one?
@ferrrett33Ā It's user friendly for anyone new to the scene of image gens, especially locally genned. They might just want to plug and play, and not have to add a node text encoder, vae, connect them etc. or might not even know how. I would say even a good bit of people don't know clip is a text encoder.
@Light7799Ā Hmm, for who exactly, even the ComfyUI workflow for Krea 2 includes the TE and VAE loaded separately. The problem with this is if we have multiple models they take up insane amounts of disk space and no way to trim them. AIO's haven't been a thing really, if you look at hundreds of models here on this website beyond SD and SDXL I mean.
@Stable_YogiĀ GGUF are slow.
@ferrrett33Ā You can use the same workflow. Just disable and bypass the TE and VAE nodes. If you experiment with many models, then of course it's best to keep them apart to save space. But AIO is a better choice if you stick to few models. Pre-merging LoRa into a base model also works better, instead of doing calculations on the fly.
With this quality.. I assume the data was AI-generated... What a waste of time and the model's potential....
Your website does not allow completing a download on slower connections. Even 9GB did not complete in 15 min. Wasted bandwidth.
There might be some network issues at that time , but everything works fine, You can retry on small models and confirm. If you face any issues ping me on chat.
Thanks
It doesn't even suck. Welcome to Pony
It is a weird thing to say on an AI website, but I think this is genuinely best described as AI slop.
ok this is my new default krea 2 model, it works great, i only wish there was a INT8 version too.
Try the Q8 on version 1.5.
@Stable_YogiĀ his talking about the new int8_convrot quantization. not gguf 8bit
@Stable_YogiĀ gguf is much slower
@jimzlfĀ Yeah that's normal with GGUFs, i will prepare the INT8 and upload soon.
Someone have a wf for this? Also: What does the pro version have over this one? Thanks.
Pro version is more vibrant with extra data and refining. Currently Krea2 Pro versions are free, you can grab here https://stableyogi.com
All other krea2 models and aio work but yours gives me this error:
RuntimeError: mat1 and mat2 shapes cannot be multiplied (42x2560 and 4096x2560)
if i load clip model separately it works.
I have removed the AIO and added the FP8 without the Clip , Try that.
@delta45424155 which clip model and vae did you use?
@ogbtjyqat450Ā standard ones for any Krea2
What is second file is for?
Which file , please be specific ?
@Stable_YogiĀ at the moment of commenting there was a 400mb file, I see you uploaded checkpoint iinsted. So nvm I guess
Details
Files
museByStableYogi_v10TurboFP8.gguf
Mirrors
Krea2 Muse Turbo Q8 - Krea2 - 8steps,cfg1,euler+simple.gguf
Krea2 Muse Turbo Q8 - Krea2 - 8steps,cfg1,euler+simple.gguf
Krea2 Muse Turbo Q8 - Krea2 - 8steps,cfg1,euler+simple.gguf
Krea2 Muse Turbo Q8 - Krea2 - 8steps,cfg1,euler+simple.gguf
Krea2 Muse Turbo Q8 - Krea2 - 8steps,cfg1,euler+simple.gguf
Krea2 Muse Turbo Q8 - Krea2 - 8steps,cfg1,euler+simple.gguf