The original author of this model is Lykon. Shakker is committed to promoting the sharing and exchange of original models, so it has reprinted the model for everyone's non-commercial communication, learning and use. Users who use this model are asked to abide by the license stated by the original author.

DreamShaper XL - Now Turbo!

Also check out the 1.5 DreamShaper page

Check the version description below (bottom right) for more info and add a ❤️ to receive future updates.
Do you like what I do? Consider supporting me on Patreon 🅿️ to get exclusive tips and tutorials, or feel free to buy me a coffee ☕

Join my Discord Server

Alpha2 is a bit old now. I suggest you switch to the Turbo or Lightning version.
DreamShaper is a general purpose SD model that aims at doing everything well, photos, art, anime, manga. It's designed to go against other general purpose models and pipelines like Midjourney and DALL-E.

"It's Turbotime"

Turbo version should be used at CFG scale 2 and with around 4-8 sampling steps. This should work only with DPM++ SDE Karras (NOT 2M). You can use this with LCM sampler, but don't do it unless you need speed vs quality.
Sampler comparison at 8 steps: https://civitai.com/posts/951781
UPDATE: Lightning version targets 3-6 sampling steps at CFG scale 2 and should also work only with DPM++ SDE Karras. Avoid going too far above 1024 in either direction for the 1st step.

No need to use refiner and this model itself can be used for highres fix and tiled upscaling.
Examples have been generated using Auto1111, but you can achieve similar results with this ComfyUI Workflow: https://pastebin.com/79XN01xs

Basic style comparison: https://civitai.com/images/4427452

If you train on this, make sure to use DPM++ SDE sampler and appropriate steps/cfg.

Keep in mind Turbo currently cannot be used commercially unless you get permission from StabilityAI. Get a membership here: https://stability.ai/membership

You can use the Turbo version (not Lightning) as a non-Turbo model with DPM++ 2M SDE Karras / Euler at cfg 6 and 20-40 steps. Here is a comparison I made with some of the best non-Turbo XL models (with regular settings and turbo settings): https://civitai.com/posts/1414848
I have no idea why anyone would prefer 40 steps over 8, but you have the option.

Old description referring to Alpha 2 and before

Finetuned over SDXL1.0.
Even if this is still an alpha version, I think it's already much better compared to the first alpha based on xl0.9.
For the workflows you need Math plugins for comfy (or to reimplement some parts manually).
Basically I do the first gen with DreamShaperXL, then I upscale to 2x and finally a do a img2img steo with either DreamShaperXL itself, or a 1.5 model that i find suited, such as DreamShaper7 or AbsoluteReality.

What does it do better than SDXL1.0?

No need for refiner. Just do highres fix (upscale+i2i)Better looking peopleLess blurry edges75% better dragons 🐉Better NSFW

Old DreamShaper XL 0.9 Alpha Description

Finally got permission to share this. It's based on SDXL0.9, so it's just a training test. It definitely has room for improvement.

Workflow for this one is a bit more complicated than usual, as it's using AbsoluteReality or DreamShaper7 as "refiner" (meaning I'm generating with DreamShaperXL and then doing "highres fix" with AR or DS7).

Results are quite nice for such an early stage.

I might disable the comment section as I'm sure some people will judge this even if it's early stage. I also don't think this is on par with SD1.5 DreamShaper yet, but it's useless to pour resources into this as SDXL1.0 is about to be released.

Have fun and make sure to add a ❤️ to receive future updates.

Non commercial license is forced by Stability at the moment.

Turbo version should be used at CFG scale 2 and with around 4-8 sampling steps. Should work with DPM++ SDE Karras (or Normal). Comparison of other samplers: https://civitai.com/posts/951781

Can be used for highres fix and tiled upscaling. Please check the examples.

If you train on this, make sure to use DPM++ SDE.

What's new in 2.1
Fixes a skin issue that sometimes occurred in v1 and v2. I used targeted adversarial learning for it.
The problem didn't affect SFW versions of the model, so I won't update that one.
It should have little to no effect on most images compared to v2, except other minor improvements on anime stuff apparently (which was totally collateral).