Text-to-Image
Diffusers
Safetensors
StableDiffusion3Pipeline
stable-diffusion
stable-diffusion-diffusers
full
Instructions to use terminusresearch/stable-diffusion-3.0-medium_reality-mix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use terminusresearch/stable-diffusion-3.0-medium_reality-mix with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("terminusresearch/stable-diffusion-3.0-medium_reality-mix", dtype=torch.bfloat16, device_map="cuda") prompt = "unconditional (blank prompt)" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit History
-
Trained for 0 epochs and 7000 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: Nonee8d2bb7 -
Trained for 0 epochs and 6500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: Nonebf7b676
-
Trained for 0 epochs and 6000 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None00dcbcc -
Trained for 0 epochs and 5500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None0e66db7 -
Trained for 0 epochs and 5000 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None3e0a6fc -
Trained for 0 epochs and 4500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None835a4a8 -
Trained for 0 epochs and 4000 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None5287162 -
Trained for 0 epochs and 3500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: Nonec263bdf -
Trained for 0 epochs and 3000 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None8153211 -
Trained for 0 epochs and 2500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None9f67aa2
-
Trained for 0 epochs and 2000 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None89db4f4 -
Trained for 0 epochs and 1500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: Nonee64c98d -
Trained for 0 epochs and 1000 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: Nonef9db62d -
Trained for 0 epochs and 500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None571afa1 -
Trained for 0 epochs and 2500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: Nonebd800e1 -
Trained for 0 epochs and 2000 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None746b305 -
Trained for 0 epochs and 1500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: Noneacbf867 -
Trained for 0 epochs and 1000 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: None03bde3c -
Trained for 0 epochs and 500 steps.
Verified signatureTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3'] Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps. Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False Using 'trailing' timestep spacing. Base model: stabilityai/stable-diffusion-3-medium-diffusers VAE: Noneb5d3e34