Downloads · 30 days
0
Counterfeit-V3.0
Lank1906/Counterfeit-V3.0
Counterfeit-V3.0 is a text-to-image model from Lank1906. Use it when you need an image from a text prompt. The card lists the license as creativeml-openrail-m.
・I have utilized BLIP-2 as a part of the training process. Natural language prompts might be more effective. ・I prioritize the freedom of composition, which may result in a higher possibility of anatomical errors. ・Th…
Access
Public
Updated Apr 8, 2026
Repo size
40 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors21.4 GB · 100%
At a glance
- Task
- Text-to-Image
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026
- SHA
- fb60a51d
Model card
From the Hugging Face model README
Counterfeit-V3.0
・I have utilized BLIP-2 as a part of the training process. Natural language prompts might be more effective.
・I prioritize the freedom of composition, which may result in a higher possibility of anatomical errors.
・The expressiveness has been improved by merging with negative values, but the user experience may differ from previous checkpoints.
・I have uploaded a new Negative Embedding, trained with Counterfeit-V3.0.
There's likely no clear superiority or inferiority between this and the previous embedding, so feel free to choose according to your preference.Note that I'm not specifically recommending the use of this embedding.
Sample image
prompt & Setting: https://civitai.com/models/4468/counterfeit-v30
- Task
- Text-to-Image
- License
- creativeml-openrail-m
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026