Instructions to use ChrisColeTech/Mage-Flow with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ChrisColeTech/Mage-Flow with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ChrisColeTech/Mage-Flow", 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 Settings
- Draw Things
- DiffusionBee
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
|
| 13 |
# Mage-Flow Turbo + Edit Turbo
|
| 14 |
|
| 15 |
-
4-step photographic text-to-image (**
|
| 16 |
and a companion instruction-editing model that takes up to **three**
|
| 17 |
reference images.
|
| 18 |
|
|
@@ -43,7 +43,7 @@ lighting and camera are preserved; only what the instruction names changes.
|
|
| 43 |
|
| 44 |
<table>
|
| 45 |
<tr><td><img src="https://huggingface.co/ChrisColeTech/Mage-Flow/resolve/main/samples/portrait.png" width="250" alt="reference"></td><td><img src="https://huggingface.co/ChrisColeTech/Mage-Flow/resolve/main/samples/edit-hat.png" width="250" alt="edit: put a brown flat cap on his head"></td><td><img src="https://huggingface.co/ChrisColeTech/Mage-Flow/resolve/main/samples/edit-beach.png" width="250" alt="edit: change the background to a sunny beach"></td></tr>
|
| 46 |
-
<tr><td><sub>**reference** β the seed-99 portrait above</sub></td><td><sub>**instruction:** `put a brown flat cap on his head` β 4 steps, seed 7 (
|
| 47 |
</table>
|
| 48 |
|
| 49 |
Both edits keep the subject essentially pixel-identical β same skin detail,
|
|
@@ -69,7 +69,7 @@ Values these builds are run with in practice.
|
|
| 69 |
|
| 70 |
- **Four steps is correct.** Both variants are step-distilled at guidance 1.0;
|
| 71 |
raising either is not the lever for quality.
|
| 72 |
-
- **Editing costs far more than generating** β
|
| 73 |
the reference must be encoded through the VL tower before denoising begins.
|
| 74 |
That asymmetry is inherent to the architecture, not a misconfiguration.
|
| 75 |
- **Write edits as instructions, not descriptions** β `put a brown flat cap on
|
|
|
|
| 12 |
|
| 13 |
# Mage-Flow Turbo + Edit Turbo
|
| 14 |
|
| 15 |
+
4-step photographic text-to-image (**β3 s** per 1024Β² image on an RTX 5090)
|
| 16 |
and a companion instruction-editing model that takes up to **three**
|
| 17 |
reference images.
|
| 18 |
|
|
|
|
| 43 |
|
| 44 |
<table>
|
| 45 |
<tr><td><img src="https://huggingface.co/ChrisColeTech/Mage-Flow/resolve/main/samples/portrait.png" width="250" alt="reference"></td><td><img src="https://huggingface.co/ChrisColeTech/Mage-Flow/resolve/main/samples/edit-hat.png" width="250" alt="edit: put a brown flat cap on his head"></td><td><img src="https://huggingface.co/ChrisColeTech/Mage-Flow/resolve/main/samples/edit-beach.png" width="250" alt="edit: change the background to a sunny beach"></td></tr>
|
| 46 |
+
<tr><td><sub>**reference** β the seed-99 portrait above</sub></td><td><sub>**instruction:** `put a brown flat cap on his head` β 4 steps, seed 7 (β88 s)</sub></td><td><sub>**instruction:** `change the background to a sunny beach with the ocean behind him` β 4 steps, seed 7 (β60 s)</sub></td></tr>
|
| 47 |
</table>
|
| 48 |
|
| 49 |
Both edits keep the subject essentially pixel-identical β same skin detail,
|
|
|
|
| 69 |
|
| 70 |
- **Four steps is correct.** Both variants are step-distilled at guidance 1.0;
|
| 71 |
raising either is not the lever for quality.
|
| 72 |
+
- **Editing costs far more than generating** β β60β90 s versus β3 s, because
|
| 73 |
the reference must be encoded through the VL tower before denoising begins.
|
| 74 |
That asymmetry is inherent to the architecture, not a misconfiguration.
|
| 75 |
- **Write edits as instructions, not descriptions** β `put a brown flat cap on
|