Download
1 variant available
290 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1430 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
7380 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
No reviews yet
Jul 4, 2026
Version upload (v1)
Field Value
Version name v1
Base model Flux.1 D
Trained words Anjali_Zit
Upload file Anjali_Zit.safetensors

130 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
60 1 2 3 4 5 6 7 8 9
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.
Description (paste into the Description box)
```
Anjali_Zit — Flux.1 D character LoRA trained on curated reference set.
Trigger: Anjali_Zit
Recommended settings:
- Base model: Flux.1 D (Dev)
- LoRA strength: 1.0
- Steps: 28
- Guidance / CFG: 3.5
- Sampler: default Flux scheduler
- Resolution: portrait 3:4 or 9:16 preferred
Prompting tips:
- Always start the prompt with the trigger word: "Anjali_Zit, <description>"
- Best at chest-up portraits and full-body editorial shots
- Handles ethnic wardrobe (saree, salwar, lehenga) well
- For photorealism, add: "photorealistic, medium format film photography aesthetic, natural skin pores"
Preview images:
- All 3 previews rendered on fal.ai flux-lora endpoint at strength 1.0, 28 steps, guidance 3.5
- Outfit lock: red and gold silk saree with gold zari border
Note: There is also an unrelated "Anjali" LoRA (Civitai model 2626821) — this one (Anjali_Zit) is a separate person, trained on fal.ai.
Training source: fal.ai flux-lora-fast-training, ~1500 steps.
