CHEYENNE_v20.safetensors

6.46 GB · SafeTensor · fp16 · full

Mitgliedschaft erforderlich

<cheyenne-xl>

IMPORTANT : Use this VAE instead.. The one took on Civitai list seems to be a problem : Suggested to me for the time I spend on these models and if you like what I do here, please considerate to donate on this Ko-Fi page : __Version 2.4 update_______________________________________________________________________ IMPORTANT : Use Skip:-2 in ComfyUI because I merge a bit of a Illustrious model !! ( Thanks Marc for feedback!) After more than 300 fusions, I wanted to propose a new paradigm for my CheyenneSDXL model: hyper illustration. It's not perfect, but it gives me new horizons and the freedom to explore different styles... I hope you enjoy it. If you like it, please follow me on and/or .. More versions to come ( back to western comics ). Again thanks for support, feedbacks and shared images on the gallery. Kisses ! __Version 2.2 update _______________________________________________________________________ Sorry for the long absence! Cheyenne V2.2 is definitely more versatile and is capable of offering more types of rendering. I'd say it's a little less 2D and more 2.5D, but don't worry, I've kept some incredible versions created during its manufacture that will fill that gap. I'm sticking to low CFGs, which suit me well (max. 3 or 3.5), after which the colors are too saturated for me and a few artifacts may occur. Then you have to test the sampling methods because the results depend on them so much. Cheyenne and my other models are made for pleasure, in my spare time, for my students and my courses. They're free and unique. They reflect my love of art and my passion for images. There's no need to pour out your opinions on their obsolescence, because Flux or anything else, because there's so much better... I know, but I don't care. Consistency at the prompt, realism, all that is great but I'm not looking for THE answer but rather to raise questions. Thanks to those who have encouraged me to continue with ko-fi donations and messages of support. Almost 1000 followers !!! Thanks for all fo you.. it warms my heart. Alternatives versions are on the way ! Stay tuned ! Kisses! __Version CH.01 [ALT] Clean Lineart update_ _________________________________ This version of is not an official version ( cf. _ ) but rather an interesting alternative for certain features, and for this one, it's its clear and precise lineart, flat colors and beautiful gradients. So if you're looking for a less organic, more cartoony version of , perhaps this version will suit your projects. As this is a tuned version of the original, the are fully compatible for even greater flexibility.) Take care.. Much love. Kisses ! __Version 2.0 update_______________________________________________________________________ This update is my most ambitious to date and I hope you'll enjoy it... I know there's Flux, SD3.5, etc... but I think there's still a bit of room for models that are a bit more personal and with a bit more writing... I'm still giving this approach a try and thanks to those who follow me! V2.0: More mature, more ‘Painting’ and ‘Matte painting’ oriented, I've refined the lineart which is more precise, I've reworked the hands a bit even though there are still some small problems but I really like this version (and others made during the training, but I'll be making LORAS as an add-on, I think). Please follow me on and and if you can, make a small donation on if you like the modele, thanks ! This version is extremely sensitive to the nature of the sampler, steps and CFG so you'll have to test what's best for you but overall : - DPM++ 2M // 10-30 steps // CFG 1-5 will essentially do the job. - DPM++ 2M SDE and DPM++ 3M SDE are excellent alternatives, with images that are often crisper and more accomplished (but less sticky to the prompt). __Version 1.8 update_______________________________________________________________________ Hi friends, it's been a while hasn't it?! I know you've got a lot of exploring to do with Flux things but maybe you can spare a little time for this update of CHEYENNE ( probably its last in SDXL version )... I've been working on it for a few months and the style is more speed painting and concept-oriented than comics, but I'm staying true to my desire to build production-oriented models and this one is incredible! More coherent update and refinings. Thanks for support ! Hope you will enjoy it. This version is extremely sensitive to the nature of the sampler, steps and CFG so you'll have to test what's best for you but overall : - DPM++ 2M // 10-30 steps // CFG 1-5 will essentially do the job. - DPM++ 2M SDE and DPM++ 3M SDE are excellent alternatives, with images that are often crisper and more accomplished (but less sticky to the prompt). I hope you enjoy this, and hopefully the next OPUS will be a FLUX version! Kisses and take care! Version 1.6 Update ___________________________________________________________ The update I'd been wanting to do for a long time: 3 weeks of hard work, over 300 mergers... At last I've arrived at the foundations of the model I'd originally envisaged. There's still room for improvement, but now I'm going to concentrate on the 'production' part and make it a more specific tool for people in the business, or for my students and friends. Thanks to for his support on KO-FI, it means a lot to me to have the recognition of the people you love. Thanks also to Marc Quentel and Thomas from for your precious advices. This is probably Cheyenne's last public update, so make the most of it! Subsequent updates will be discreetly passed on to my followers. Thank you for all the encouragement I've received and those who've posted in the gallery. You are beautiful and brave. I love you all! >So what's new? - A massive update of styles and flexibility (this involves better management of the CFG, which now plays an essential role! From 1.5 (rougher, sketchy) to 4-5 (good medium mix) to 7-8 (more contrast, flatter, outline)... and also more real

SHA256

7363E6274CC5C121C75AC10D8D25F0CDD4365964B1424DDC8BB40FE2F50E923C

ModelTrends.ai-Modell-ID

#7571

Sampler

DPM++ 2M

Schritte

20

Guidance

2

Seed

14043405

Größe

768x1224

Sampler

DPM++ 3M SDE

Schritte

20

Guidance

2

Seed

2638863151

Größe

832x1216

Clip skip

3

Sampler

DPM2

Schritte

26

Guidance

4.5

Seed

1521240680

Größe

832x1216

Clip skip

2

Sampler

DPM++ 2M

Schritte

15

Guidance

2

Seed

1390116037

Größe

832x1216

Sampler

DPM++ 2M Karras

Schritte

40

Guidance

4

Seed

1004049149

Größe

832x1216

Clip skip

2

Sampler

DPM++ 3M SDE

Schritte

8

Guidance

1.5

Seed

2572194438

Größe

832x1216

Sampler

DPM2 a

Schritte

19

Guidance

3

Seed

1349023707

Größe

832x1216

Clip skip

2