Scheduler = om_pretrained(model_id, subfolder= "scheduler") Model_id = "CompVis/stable-diffusion-v1-4" # Use the Euler scheduler here instead To swap out the noise scheduler, pass it to from_pretrained: from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler You can do so by telling diffusers to expect the weights to be in float16 precision: import torch If you are limited by GPU memory and have less than 4GB of GPU RAM available, please make sure to load the StableDiffusionPipeline in float16 precision instead of the default float32 precision as done above. Prompt = "a photo of an astronaut riding a horse on mars" Pipe = om_pretrained(model_id, torch_dtype=torch.float16) Model_id = "CompVis/stable-diffusion-v1-4" Running the pipeline with the default PNDM scheduler: import torchįrom diffusers import StableDiffusionPipeline Pip install -upgrade diffusers transformers scipy We recommend using 🤗's Diffusers library to run Stable Diffusion. Resources for more information: GitHub Repository, Paper.Ĭite as: = , It is a Latent Diffusion Model that uses a fixed, pretrained text encoder ( CLIP ViT-L/14) as suggested in the Imagen paper. Model Description: This is a model that can be used to generate and modify images based on text prompts.
See also the article about the BLOOM Open RAIL license on which our license is based. License: The CreativeML OpenRAIL M license is an Open RAIL M license, adapted from the work that BigScience and the RAIL Initiative are jointly carrying in the area of responsible AI licensing.
Model type: Diffusion-based text-to-image generation model If you are looking for the weights to be loaded into the CompVis Stable Diffusion codebase, come hereĭeveloped by: Robin Rombach, Patrick Esser This weights here are intended to be used with the 🧨 Diffusers library. The Stable-Diffusion-v1-4 checkpoint was initialized with the weights of the Stable-Diffusion-v1-2Ĭheckpoint and subsequently fine-tuned on 225k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input.įor more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion with 🧨Diffusers blog.
0 kommentar(er)
