AILTech/AIL-Rendering-sd1.5
0
1---2license: creativeml-openrail-m3---4 5**Model Details**6 7Developed by: AIL-tech8Model type: Diffusion-based text-to-image generative model9Model Description: AIL-Rendering-sd1.5-v10 is the first version of this model, fine-tuned for 600k steps. It can generate high-quality renderings more accurately from tag prompts.10License: CreativeML Open RAIL++-M License11Fine-tuned from: SD 1.512 13 14**Special Tags**15 16Quality tags include: masterpiece, best quality, high quality, good quality, normal quality, low quality, worst quality.17 18 19**Recommended settings**20 21To guide the model towards generating high-aesthetic images, use negative prompts like:22lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry23 24For higher quality outcomes, prepend prompts with:25((masterpiece, best quality)), highres,26 27it’s recommended to use a lower classifier-free guidance (CFG Scale) of around 6-8, sampling steps below 30, clip skip set to 2, and to use Euler Ancestral (Euler a) as a sampler. Also could try DPM adaptive, which is slower but might give a better result.28 29 30**Multi Aspect Resolution**31 32This model supports generating images at the following dimensions:33768 x 768, 704 x 832, 640 x 896, 576 x 960, 518 x 1088, 518 x 1152, 448 x 1216, 448 x 1280, 384 x 147234 35 36**The Future Plan:**37 38This model is the first attempt at training an architecture-specific model, and a SDXL version will be released subsequently."39 40 41**Contect**42 43AILabs-AIGC@outlook.com44 45 46**Sample Generated Images (Could be download in the image folder)**4748495051525354555657 58 59 60