...
https://docs.bfl.ai/guides/prompting_guide_flux2
| Hex Colors | Brand work, precise matching | color #FF5733 or hex #FF5733 |
| Camera References | Photorealism | shot on [camera], [lens], [settings] |
| Style Eras | Period-specific looks | 80s vintage, 2000s digicam |
| Multi-Reference | Composite images | [pro]: 8, [flex]: 10, [dev]: ~6 |
| Seed | Reproducible results | seed: 42 |
| Guidance [flex] | Prompt adherence | guidance: 4.5 (1.5-10) |
| Steps [flex] | Quality vs speed | steps: 50 (16-50) |
| Aspect Ratios | Use case optimization | 1:1, 16:9, 9:16, 4:3, 21:9 |
| Code Block |
|---|
prompt = "Realistic macro photograph of a hermit crab using a soda can as its shell, partially emerging from the can, captured with sharp detail and natural colors, on a sunlit beach with soft shadows and a shallow depth of field, with blurred ocean waves in the background. The can has the text `BFL Diffusers` on it and it has a color gradient that start with #FF5733 at the top and transitions to #33FF57 at the bottom."
image = pipe(
prompt_embeds=remote_text_encoder(prompt),
#image=load_image("https://huggingface.co/spaces/zerogpu-aoti/FLUX.1-Kontext-Dev-fp8-dynamic/resolve/main/cat.png") #optional image input
generator=torch.Generator(device=device).manual_seed(42),
num_inference_steps=50, #28 steps can be a good trade-off
guidance_scale=4,
).images[0] |
...
Time: 23m 18.46s | total 1414.43 pipeline 1392.03 gc 9.53 callback 7.91 decode 2.23 post 1.45 init 1.35 vae 0.94 prepare 0.44 | GPU 111078 MB 88% | RAM 108.82 GB 88%
| 4 | 8 | 16 | 32 | 50 | |
|---|---|---|---|---|---|
| CFG1 |
|
|
|
|
|
| CFG2 |
|
|
|
|
|
| CFG3 |
|
|
|
|
|
| CFG4 |
|
|
|
|
|
| CFG5 |
|
|
|
|
|
| CFG6 |
|
|
|
|
|
| CFG8 |
|
|
|
|
|
Test 2 - Face and hand
...
285H Time: 9m 29.98s | total 578.81 pipeline 565.66 gc 7.02 callback 3.23 decode 1.43 post 0.88 init 0.85 vae 0.62 prepare 0.29 | GPU 118690 MB 94% | RAM 115.96 GB 94%
| 8 | 16 | 20 | 32 | 50 | |||
|---|---|---|---|---|---|---|---|
| CFG1 |
|
|
|
|
| ||
| CFG2 |
|
|
|
|
| ||
| CFG3 |
|
|
|  |
| ||
| CFG4 |
|
|
|
|
| CFG5 | |
| CFG5 |  |
|
|
|
| ||
| CFG6 |
|
|
|
|
| ||
| CFG7 |
|
|
|
|
| CFG6 | CFG7
Test 3 - Legs
Prompt: Prompt: Generate a photo of a woman's legs, with her feet crossed and wearing white high-heeled shoes with ribbons tied around her ankles. The shoes should have a pointed toe and a stiletto heel. The woman's legs should be smooth and tanned, with a slight sheen to them. The background should be a light gray color. The photo should be taken from a low angle, looking up at the woman's legs. The ribbons should be tied in a bow shape around the ankles. The shoes should have a red sole. The woman's legs should be slightly bent at the knee.
...
285H Time: 22m 13.21s | total 1360.17 pipeline 1333.18 onload 7.85 offload 7.40 callback 6.99 vae 4.71 | GPU 22796 MB 36% | RAM 40.32 GB 65%
| 8 | 16 | 32 | 64 | |
|---|---|---|---|---|
| CFG2 |
|
|
|
|
| CFG4 |
|
|
|
|
| CFG6 |
|
|
|
|
| CFG8 |
|
|
|
|
| CFG10 |
|
|
|
|
Test 4 CivitAi profile cover generation
Prompt: image with 5 canvases and one android robot painting on the 3rd canvas. first two is done with some futuristic images, last two is blank. robot is surprised look back at the camera. paint brush is in the robot hand. Left bottom corner text "Flux.2 dev"
Parameters: Steps: 32| Size: 1600x400| Seed: 4014230639| CFG scale: 8
Prompt: with analog noise and glitches, CivitAi cover image with 5 canvases and one android robot painting on the 3rd canvas. first two is done with some futuristic images, last two is blank. robot is surprised look back at the camera. paint brush is in the robot hand.
Parameters: Steps: 32| Size: 1600x400| Seed: 2404111820| CFG scale: 3.5
Prompt: CivitAi cover image with 5 canvases and one android robot painting on the 3rd canvas. first two is done with some futuristic images, last two is blank. robot is surprised look back at the camera. paint brush is in the robot hand. Left bottom corner text "SD.Next + Flux.2 Dev", upper right corner text "Stable Diffusion at home"
Parameters: Steps: 50| Size: 1600x400| Seed: 978455805| CFG scale: 4
Prompt: LEGO style, CivitAi cover image with 5 canvases and one android robot painting on the 3rd canvas. first two is done with some futuristic images, last two is blank. robot is surprised look back at the camera. paint brush is in the robot hand. Left bottom corner text "SD.Next + Flux.2 Dev", upper right corner text "Stable Diffusion at home"
...
Test 5 - Empty prompts
1024x1024, Steps 50
seed 1 |
seed 2 |
seed 3 |
seed 4 |
seed 5 |
seed 6 |
seed 7 |
seed 8 |
seed 9 |
seed 10 |
seed 21 |
seed 38 |
seed 42 | sweed 68 |
seed 2025 |
Test 6 - Other Models cover
+ random seed
Test 7 - Art Prompts
System info
| Code Block |
|---|
Mon Dec 8 14:39:24 2025 app: sdnext.git updated: 2025-12-06 hash: 764443213 url: https://github.com/liutyi/sdnext/tree/pytorch arch: x86_64 cpu: x86_64 system: Linux release: 6.17.0-7-generic python: 3.12.3 Torch: 2.9.1+xpu device: Intel(R) Arc(TM) Graphics (1) ram: free:118.76 used:4.31 total:123.07 xformers: diffusers: 0.36.0.dev0 transformers: 4.57.1 active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16 base: Diffusers/black-forest-labs/FLUX.2-dev [6aab690f83] refiner: none vae: none te: none unet: none Backend: ipex Pipeline: native Cross-attention: Scaled-Dot-Product |
...