coyotte

V10 (Krea 2) is OUT!

Download is available on CivitAI now. I've removed the gofile and google drive links since they are no longer needed.

🚨 Attention:

There was a bug with the fp8 version caused by a faulty fp16-to-fp8 conversion script, which resulted in blurry images lacking detail. If you encountered this issue, please re-download the file.

Sorry for the inconvenience!

Preview pics can be found on Civitai.

Available Model Variants:

Raw: fp16 / fp8 / int8_convrot
Turbo: fp16 / fp8 / int8_convrot / Q4 GGUF (reuploaded the working version) / Q2 GGUF

Hardware Recommendations:

8 GB VRAM: Your best bet is the Turbo Q4 GGUF variant.
12 GB VRAM (or if you don't mind slightly longer generation times): Go with either Turbo fp8 or Turbo int8_convrot.
24 GB VRAM: You can comfortably run the full Turbo fp16 variant.

Use Turbo for everyday inference (generation) and Raw if you plan on training or fine-tuning.

Travis Appel

how do I get this on comfy?

Aug 06 05:28

coyotteReplying to Travis Appel

Travis Appel, That depends on your 'checkpoint' definition. This is a diffusion model. It's not like SDXL, where you had Unet (Diffusion Model) + Text Encoder + VAE all-in-one. You need to add each manually.

Aug 06 19:03

Uncle Ne Dobre

Discord link is expired in DM :)

Aug 16 23:09

Jul 06 18:43

Please join my Discord channel if you haven't yet, as I often post some exclusive insights there. Every subscriber gets the access. You might need to link your DS with boosty tho.

Jun 19 18:46

V9 (Zenith) is out!

Download link: https://drive.google.com/file/

Level required:

BASIC SUPPORT

Apr 29 17:58

V9 in May. Z-Image alpha version might come out in May as well 👀

po vaj

Apparently Ideogram 4 may be the new king of AI image generation. This guy has only trained an Ideogram LoRa for a few days, training run not even close to finished yet and already it is creating better quality NSFW than Flux Klein or Zimage that has taken months for them. Ideogram seems to converge incredibly quickly in training, it seems to respond lightning fast to lora training. His sample images are out of this world(vaginas still need more training time, but it will come), maybe in a month it will be indistinguishable from Met-Art style nudes. Unfortunately the base model will not be released as it is locked behind enterprise level commercial license. So training on the quantized model is going to be very hard as distilled models are bad for training/fine tuning. Interested to hear your take on it Coyotte. https://huggingface.co/RazzzHF/Realism_Engine_Ideogram_4/tree/main

Jun 10 03:07 (changed)

coyotte

po vaj, 3) We should be careful about praising models with restrictive licenses. If we embrace them, we risk setting a precedent where every new 'open-weight' release feels entitled to impose these kinds of limitations. We’re essentially voting for a future where 'open' doesn't actually mean open.

TLDR: I REALLY don't think it's worth the risk.

Jun 10 12:42 (changed)

po vaj

Ouch, I jumped on the band wagon too soon, sigh...guess its dead in the water then.

Jun 10 18:34

Apr 11 20:25

I've noticed there's not enough good and powerful post-processing nodes for ComfyUI, so I'm working on one in parallel with work on V9 and Z-Image version.
Exclusive LUT presets will be available to my subscribers. I have a photography background, so I feel like this project will turn out interesting

po vaj

The guy that does -
https://github.com/martin-rizzo/ComfyUI-ZImagePowerNodes Has a great workflow and nodes. Creates some very nice images, but its not very compatible with loras last time I checked.

May 01 14:57

Apr 01 18:15

A Guide to the Palette Canvas Node for easy lighting control

You can get the node there: https://github.com/c0yotte/ComfyUI-PaletteCanvas

Primary Purpose and Benefits

Lighting Control: First and forem...

Level required:

BASIC SUPPORT

Mar 29 22:58

I will upload one of the ComfyUI nodes I was working on lately soon. It makes setting up the lighting for your image way easier. I'm talking about like 90% easier than without that node.

Mar 29 20:18

V8 (Apex) is out!

The link to the model: https://dri

Level required:

BASIC SUPPORT

Feb 11 11:33

Klein version soon

Key Black

I cant wait to test it

Feb 25 22:41

Sarcastic Wanderer

Any chance you will be including a workflow for the Klein version? As a new comer, I learned so much from your DMD2 workflow, I'm almost as excited to see what you might've cooked up specifically for Klein's needs. Anyways, looking forward to testing it out!

Mar 04 07:53

Oct 05 2025 11:59

I am a bit absent right now from the media due to personal IRL stuff, but I DO work on V8, Chroma loras and possibly Wan 2.2 in the free time.

Any wishes on the concepts / ideas for loras?

About

V10 (Krea 2) is OUT!

BASIC SUPPORT