![]() It's based on SDXL0.9, so it's just a training test. Just do highres fix (upscale+i2i)įinally got permission to share this. Old description referring to Alpha 2 and beforeĮven if this is still an alpha version, I think it's already much better compared to the first alpha based on xl0.9.įor the workflows you need Math plugins for comfy (or to reimplement some parts manually).īasically 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. Keep in mind Turbo currently cannot be used commercially unless you get permission from StabilityAI.You can still sell images normally. If you train on this, make sure to use DPM++ SDE sampler. ![]() ![]() ![]() No need to use refiner and can be used for highres fix and tiled upscaling.Įxamples have been generated using Auto1111, but you can achieve similar results with this ComfyUI Workflow: This should work only with DPM++ SDE Karras (or Normal). Turbo version should be used at CFG scale 2 (3-4 for styled stuff) and with around 4-7 sampling steps. It's designed to go against other general purpose models and pipelines like Midjourney and DALL-E. ![]() I suggest you switch to the Turbo version.ĭreamShaper is a general purpose SD model that aims at doing everything well, photos, art, anime, manga. DreamShaper XL - Now Turbo! Also check out the 1.5 DreamShaper pageĬheck the version description below (bottom right) for more info and add a ❤️ to receive future updates.ĭo you like what I do? Consider supporting me on Patreon □️ to get exclusive tips and tutorials, or feel free to buy me a coffee ☕Īlpha2 is a bit old now. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |