Text-to-Image
Diffusers
Safetensors
English
MMDiffPipeline
remote-sensing
optical
sar
infrared
multimodal
lora
stable-diffusion
Instructions to use BiliSakura/MMDiff-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/MMDiff-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("BiliSakura/MMDiff-diffusers") prompt = "There is a ship in the blue water on the shore." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -154,7 +154,7 @@ output.ir[0].save("demo/ir/demo.png")
|
|
| 154 |
| Steps | 50 |
|
| 155 |
| CFG (`guidance_scale`) | 7.5 |
|
| 156 |
| `torch_dtype` | `bfloat16` |
|
| 157 |
-
| Scheduler | `
|
| 158 |
| Spatial transfer | attention layers `1..9`, ResNet layer `2`, `resnet_time=1.0` |
|
| 159 |
|
| 160 |
`modalities` accepts `"all"` or any subset of `"opt"`, `"sar"`, `"ir"`. SAR/IR generation requires OPT spatial features; the pipeline runs OPT first when they are not supplied via `spatial_features`.
|
|
|
|
| 154 |
| Steps | 50 |
|
| 155 |
| CFG (`guidance_scale`) | 7.5 |
|
| 156 |
| `torch_dtype` | `bfloat16` |
|
| 157 |
+
| Scheduler | `DDIMScheduler` |
|
| 158 |
| Spatial transfer | attention layers `1..9`, ResNet layer `2`, `resnet_time=1.0` |
|
| 159 |
|
| 160 |
`modalities` accepts `"all"` or any subset of `"opt"`, `"sar"`, `"ir"`. SAR/IR generation requires OPT spatial features; the pipeline runs OPT first when they are not supplied via `spatial_features`.
|