Instructions to use zlaa/SD3.5-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zlaa/SD3.5-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("zlaa/SD3.5-medium", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Upload verified SD3.5 HTP IQ4_NL weight text_encoder_2/model_htp_repacked_iq4_nl.safetensors
Browse filesIQ4_NL HTP repacked safetensors validated on real device with 3-step and 20-step full-model runs. T5 continues to reuse text_encoder_3/model_merged_htp_repacked.safetensors.
text_encoder_2/model_htp_repacked_iq4_nl.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ab40813791ac4cd102a67bbbb4af2ac2ae5c8a7977a1e3177b23c6a1e3e2201
|
| 3 |
+
size 485018032
|