Verified: 18 days ago
SafeTensor
Type | |
Stats | 230 5 24 |
Reviews | (35) |
Published | May 7, 2025 |
Base Model | |
Training | Steps: 3,300 Epochs: 20 |
Usage Tips | Strength: 1 |
Trigger Words | diorama miniatures |
Hash | AutoV2 C946E85E83 |
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
version 1.2 brings a bit more versatility, in terms of scene, and viewpoint (overhead still works great, but other angles come easier) and subject matter.
Creating scenes of miniatures - you don't always need any key words, but it reinforces the style to start with 'diorama miniatures view of ...' or 'overhead diorama view of ...'
Flux understands this concept natively, but this LoRA's main contribution is to reduce the absurd amount of blur/bokeh the base model wants to generate and it helps to keep texture and aesthetic more consistent with less prompting.