Instructions to use stabilityai/stable-diffusion-3.5-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-diffusion-3.5-medium with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
how do i use this with ForgeUI
im trying to use it with forge ui but i keep getting error "AssertionError: You do not have CLIP state dict!"
sorry if its wrong place to ask
I'm using it in Comfyui and have the same issue
im trying to use it with forge ui but i keep getting error "AssertionError: You do not have CLIP state dict!"
If you get "AssertionError: You do not have CLIP state dict!" error probably you not set "VAE / Text Encoder"
Put Stable-diffusion to:
Forge\run\webui\models\Stable-diffusion\sd3.5_medium.safetensors
Put VAE / Text Encoder to:
Forge\run\webui\models\text_encoder\clip_g.safetensors
Forge\run\webui\models\text_encoder\clip_l.safetensors
Forge\run\webui\models\text_encoder\t5xxl_fp16.safetensors
You can get "VAE / Text Encoder" from https://huggingface.co/stabilityai/stable-diffusion-3.5-medium/tree/main/text_encoders or other place
