Text-to-Image
Diffusers
Safetensors
English
Flux2KleinPipeline
flux
flux2-klein
quantization
sdnq
4-bit precision
dynamic-quantization
low-vram
google-colab
t4
batch-image-edit
background-removal
Instructions to use codeShare/FLUX.2-klein-AIO-SDNQ-4bit-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use codeShare/FLUX.2-klein-AIO-SDNQ-4bit-dynamic with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("codeShare/FLUX.2-klein-AIO-SDNQ-4bit-dynamic", 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
Update transformer/config.json
Browse files- transformer/config.json +0 -3
transformer/config.json
CHANGED
|
@@ -3,9 +3,6 @@
|
|
| 3 |
"_diffusers_version": "0.38.0.dev0",
|
| 4 |
"_name_or_path": "/content/flux_aio_full/transformer",
|
| 5 |
"attention_head_dim": 128,
|
| 6 |
-
"auto_map": {
|
| 7 |
-
"AutoModel": "modeling_flux2.Flux2Transformer2DModel"
|
| 8 |
-
},
|
| 9 |
"axes_dims_rope": [
|
| 10 |
32,
|
| 11 |
32,
|
|
|
|
| 3 |
"_diffusers_version": "0.38.0.dev0",
|
| 4 |
"_name_or_path": "/content/flux_aio_full/transformer",
|
| 5 |
"attention_head_dim": 128,
|
|
|
|
|
|
|
|
|
|
| 6 |
"axes_dims_rope": [
|
| 7 |
32,
|
| 8 |
32,
|