Text-to-Image
Diffusers
ONNX
Safetensors
GGUF
English
art
agent
image-generation
video-generation
text-to-video
style-transfer
image-editing
tts
local-inference
Instructions to use atMrMattV/Visione with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use atMrMattV/Visione with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("atMrMattV/Visione", 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 README.md
Browse files
README.md
CHANGED
|
@@ -44,6 +44,19 @@ tags:
|
|
| 44 |
</p>
|
| 45 |
|
| 46 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
# April 10 — v0.6.0
|
| 49 |
|
|
|
|
| 44 |
</p>
|
| 45 |
|
| 46 |
---
|
| 47 |
+
## Changelog:
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
# April 11 — v0.6.1
|
| 51 |
+
|
| 52 |
+
## Quality Improvements
|
| 53 |
+
|
| 54 |
+
- **Contextual Edit** — Inference now runs at near-native resolution, matching the model's evaluation parameters. Output quality is significantly improved: sharper detail, better texture fidelity, and more accurate style transfer compared to the previous downscaled approach.
|
| 55 |
+
|
| 56 |
+
## Stability
|
| 57 |
+
|
| 58 |
+
- Contextual Edit automatically falls back to a lower resolution if the current hardware cannot complete generation at full quality, ensuring the job always completes rather than crashing.
|
| 59 |
+
|
| 60 |
|
| 61 |
# April 10 — v0.6.0
|
| 62 |
|