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 : <a target="_blank" rel="ugc" href="https://ko-fi.com/aurety">https://ko-fi.com/aurety</a>Follow me on X / Twitter to watch the updates : <a target="_blank" rel="ugc" href="https://twitter.com/AAurety">Antoine Aurety / @AAurety</a>____________________________________________________________________________________________IMPORTANT : There was a problem with my last merge on the old file, which has now been resolved (I hope!), so don't hesitate to download the file again. Sorry again!_______________________________________________________________Chinook 1.0 and Chinook 1.0_VAE are finally out and it's a liberation for me because this project went through more than 1100 merges and finetunings... I've learnt so much with this model about ‘’latent diffusion‘’ that my next models will progress exponentially. It's not a joke !! ;)Thanks again to my supporters on the KO-FI platform, it's important to me and these models represent months of work and those who make fun of mixed merges have never done one seriously... Here's an example gif of a finetuning job... ( WIP )Well then?! : _Chinook 1.0 is incredible ! aha.. It's a model that I'm trying to optimise for cinematic rendering (1536*640) but of course you can use it in the classic SDXL sizes. It's the first version, so I've still got a lot of work to do on it, but the tone is set and frankly I'm really proud of it!As it's a heavy mix, I finetuned it from low CFG (1.5-3) so that the noise would come up with more quality and detail. It also has a wide spectrum and needs to be tested assiduously!1-5 -&gt; 3: More creative, less photographic quality.3-&gt;5 : Good compromise6-&gt; 8 : More photographic and a little blurry for the cinematic side.For the sampler, I took the classic DPM++ 2M Karras, perhaps there's something better? I'll leave you to explore. For the Steps, between 10 and 100 and fixed hires, if you like!Use of Adetailer sometimes necessary.I use different VAEs for my renders, which is why I advise you to take the version WITHOUT a VAE and to add your own depending on your needs. The most incredible VAEs all come from and I encourage you to discover them all! The images in the gallery use them extensively. ( link in ressources or here <a target="_blank" rel="ugc" href="https://civarchive.com/models/152040/xlvaec">https://civarchive.com/models/152040/xlvaec</a> ) _ Take them all !! Thanks to atw44qb <a target="_blank" rel="ugc" href="https://civarchive.com/user/atw44qb">https://civarchive.com/user/atw44qb</a>For the prompt, in works equally well as a literal version (GPT/Claude text for example), or as words separated by commas.So the basis of a prompt would be, for example :Positive prompt: cinematic, film grain, RAW, movie still, realistic photography, [SUBJECT], [LIGHTING], dutch angle style, chromatic aberrationnegative prompt: drawing, illustration, 3d, sketch, cgThere are some STRONG trigger words: dutch angle style, chromatic aberration, movie style, analog,... which are very important for the cinematic side I wanted.I also worked on the notions of crowds and variety of faces.This model isn't perfect! There are still some obvious finger and eye problems and as I've mixed a lot of Loras designed for 1024x1024 or portrait style, I have to struggle with the fact that it can centre the subject (but I've worked a lot on this aspect!). In short, there's still a lot of work to do, so please be patient!I'd love to see what you will using it, please share your creations and feedbacks !! And follow me ! Thanks for using my models !Kisses !____________________________________________________________________________________________CHINOOK 0.8 finally out! This model was born from an iteration of MOHAWK and I immediately saw the potential to move towards more cinematic images! So if you're into cinema or animatic games, this model is for you! Or, if you want a realistic yet creative model, then I hope it will meet your expectations.I've just laid the foundations, but for me this model is different and I haven't found an equivalent, but it also suffers from its youth! So be patient, because it has great potential.It's the fruit of a lot of hard work and over 400 fusions, a computer crash, a hard disk crash, it's a model that's come a long way and its production was epic! aha... But it's available now, and I can't wait to see what you do with it!On the technical side:It's designed for panoramic rendering, so 1536x640 is a good ratio, but of course all sdxl formats are welcome.Parameters : DPM++ 2M Karras // Samples : 25-60 // Hires ( Optional ) // Adetailer ( Sometimes necessary ) // CFG scale : 4-8Trigger words : cinematic, movie still, filmgrab, depth of field, chromatic aberration, hyper realistic...

_CHINOOK_

__Chinook__V1.0 MASSIVE Update !!It's a model that I'm trying to optimise for cinematic rendering (1536*640) but of course you can use it in the classic SDXL sizes. It's the first version, so I've still got a lot of work to do on it, but the tone is set and frankly I'm really proud of it!As it's a heavy mix, I finetuned it from low CFG (1.5-3) so that the noise would come up with more quality and detail. It also has a wide spectrum and needs to be tested assiduously!1-5 -&gt; 3: More creative, less photographic quality.3-&gt;5 : Good compromise6-&gt; 8 : More photographic and a little blurry for the cinematic side.For the sampler, I took the classic DPM++ 2M Karras, perhaps there's something better? I'll leave you to explore. For the Steps, between 10 and 100 and fixed hires, if you like!Use of Adetailer sometimes necessary.I use different VAEs for my renders, which is why I advise you to take the version WITHOUT a VAE and to add your own depending on your needs. The most incredible VAEs all come from and I encourage you to discover them all! The images in the gallery use them extensively.For the prompt, in works equally well as a literal version (GPT/Claude text for example), or as words separated by commas.So the basis of a prompt would be, for example :Positive prompt: cinematic, film grain, RAW, movie still, realistic photography, [SUBJECT], [LIGHTING], dutch angle style, chromatic aberrationnegative prompt: drawing, illustration, 3d, sketch, cgThere are some STRONG trigger words: dutch angle style, chromatic aberration, movie style, analog,... which are very important for the cinematic side I wanted. I also worked on the notions of crowds and variety of faces.This model isn't perfect! There are still some obvious finger and eye problems and as I've mixed a lot of Loras designed for 1024x1024 or portrait style, I have to struggle with the fact that it can centre the subject (but I've worked a lot on this aspect!). In short, there's still a lot of work to do, so please be patient!

CHINOOK_v10.safetensors

_CHINOOK_1.0.fp16.safetensors

v1.0

v1.00_vae_baked

0.8 (VAE baked)

Version with vae : madebyollin_sdxl_vae_fix.safetensors Consider to use the other version if you can for more options with VAE finishing !More info on the version without VAE.. <a target="_blank" rel="ugc" href="https://civitai.com/models/400589">https://civitai.com/models/400589</a>Chinook 1.0 is finally out and it's a liberation for me because this project went through more than 1100 merges and finetunings... I've learnt so much with this model about ‘’latent diffusion‘’ that my next models will progress exponentially. It's not a joke !! ;)Thanks again to my supporters on the KO-FI platform, it's important to me and these models represent months of work and those who make fun of mixed merges have never done one seriously... Here's an example gif of a finetuning job... ( WIP )Well then?! : _Chinook 1.0 is incredible ! aha.. It's a model that I'm trying to optimise for cinematic rendering (1536*640) but of course you can use it in the classic SDXL sizes. It's the first version, so I've still got a lot of work to do on it, but the tone is set and frankly I'm really proud of it!As it's a heavy mix, I finetuned it from low CFG (1.5-3) so that the noise would come up with more quality and detail. It also has a wide spectrum and needs to be tested assiduously!1-5 -&gt; 3: More creative, less photographic quality.3-&gt;5 : Good compromise6-&gt; 8 : More photographic and a little blurry for the cinematic side.For the sampler, I took the classic DPM++ 2M Karras, perhaps there's something better? I'll leave you to explore. For the Steps, between 10 and 100 and fixed hires, if you like!Use of Adetailer sometimes necessary.For the prompt, in works equally well as a literal version (GPT/Claude text for example), or as words separated by commas.So the basis of a prompt would be, for example :Positive prompt: cinematic, film grain, RAW, movie still, realistic photography, [SUBJECT], [LIGHTING], dutch angle style, chromatic aberrationnegative prompt: drawing, illustration, 3d, sketch, cgThere are some STRONG trigger words: dutch angle style, chromatic aberration, movie style, analog,... which are very important for the cinematic side I wanted.I also worked on the notions of crowds and variety of faces.This model isn't perfect! There are still some obvious finger and eye problems and as I've mixed a lot of Loras designed for 1024x1024 or portrait style, I have to struggle with the fact that it can centre the subject (but I've worked a lot on this aspect!). In short, there's still a lot of work to do, so please be patient!I'd love to see what you will using it, please share your creations and feedbacks !! And follow me ! Thanks for using my models !Kisses !

Files with SHA256: 59681d5417f8905ff0331b8bfb4b5a60724d7bf3c02dec2eba67d72a93563021