Info

DevOps > Test 58 - FLUX.2-dev-SDNQ-uint4-svd-r32 > 2025-11-26-00001-FLUX.2-dev-SDNQ-uint4-svd-r32-1024x1024-Seed2926064816-CFG6-AG0-STEP20.jpg

Prompt: Cowboy holding a pole of road sign with text "Flux.2 Dev". text "32B" is handwritten on a corner of the sign. Golden Gate bridge on the background.

Time: 30m 12.49s | total 1838.65 pipeline 1812.42 callback 7.92 onload 7.76 vae 6.12 offload 4.37 | GPU 36128 MB 28% | RAM 48.28 GB 39%

Prompt: Cowboy holding a pole of road sign "Flux.2 Dev". 32B is handwritten on a corner of the sign. Golden Gate bridge on the background.

https://huggingface.co/black-forest-labs/FLUX.2-dev

https://docs.bfl.ai/guides/prompting_guide_flux2

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]

Test 0 - Different seed variations

Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling

Prompt: Create a close-up photograph of a woman's face and hand, with her hand raised to her chin. She is wearing a white blazer and has a gold ring on her finger. Her nails are neatly manicured and her hair is pulled back into a low bun. She is smiling and has a radiant expression on her face. The background is a plain light gray color. The overall mood of the photo is elegant and sophisticated. The photo should have a soft, natural light and a slight warmth to it. The woman's hair is dark brown and pulled back into a low bun, with a few loose strands framing her face.

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.

CFG4, STEP50	Seed: 1620085323	Seed:1931701040	Seed:4075624134	Seed:2736029172
bookshop girl
hand and face
legs and shoes

Test 1 - Bookshop

Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling

	8	16	20	32	50
CFG1
CFG2
CFG3
CFG4
CFG5
CFG6
CFG7

Test 2 - Face and hand

Prompt: Create a close-up photograph of a woman's face and hand, with her hand raised to her chin. She is wearing a white blazer and has a gold ring on her finger. Her nails are neatly manicured and her hair is pulled back into a low bun. She is smiling and has a radiant expression on her face. The background is a plain light gray color. The overall mood of the photo is elegant and sophisticated. The photo should have a soft, natural light and a slight warmth to it. The woman's hair is dark brown and pulled back into a low bun, with a few loose strands framing her face.

	8	16	20	32	50
CFG1
CFG2
CFG3
CFG4
CFG5
CFG6
CFG7

Test 3 - Legs

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.

	8	16	20	32	50
CFG1
CFG2
CFG3
CFG4
CFG5
CFG6
CFG7

Test 4 CivitAi profile cover generation

DevOps > Test 58 - FLUX.2-dev-SDNQ-uint4-svd-r32 > 2025-11-26-00003-FLUX.2-dev-SDNQ-uint4-svd-r32-1600x400-Seed4014230639-CFG8-AG0-STEP32.jpg

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

DevOps > Test 58 - FLUX.2-dev-SDNQ-uint4-svd-r32 > 2025-11-26-00004-FLUX.2-dev-SDNQ-uint4-svd-r32-1600x400-Seed2404111820-CFG3.5-AG0-STEP32.jpg

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

DevOps > Test 58 - FLUX.2-dev-SDNQ-uint4-svd-r32 > 2025-11-27-00005-FLUX.2-dev-SDNQ-uint4-svd-r32-1600x400-Seed978455805-CFG4-AG0-STEP50.jpg

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

DevOps > Test 58 - FLUX.2-dev-SDNQ-uint4-svd-r32 > 2025-11-27-00006-FLUX.2-dev-SDNQ-uint4-svd-r32-1600x400-Seed1179249187-CFG4-AG0-STEP50.jpg

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"

Parameters: Steps: 50| Size: 1600x400| Seed: 1179249187| CFG scale: 4

Test 5 CFG 4 vs CFG 6

CFG4
CFG6

Test 6 - Empty prompts

1024x1024, Steps 20

seed 1	seed 2	seed 3	seed 4	seed 5
seed 6	seed 7	seed 8	seed 9
seed 42	seed 324	seed 777

Test 7 - Other Models cover

Test 8 - Art Prompts

System info

Wed Nov 26 20:17:09 2025
app: sdnext.git updated: 2025-11-26 hash: 38e4541ea url: https://github.com/liutyi/sdnext/tree/pytorch
arch: x86_64 cpu: x86_64 system: Linux release: 6.14.0-36-generic
python: 3.12.3 Torch: 2.9.1+xpu 
device: Intel(R) Arc(TM) Graphics (1)
 
ram: free:105.18 used:20.15 total:125.33
 
xformers: diffusers: 0.36.0.dev0 transformers: 4.57.1
active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16
base: Diffusers/Disty0/FLUX.2-dev-SDNQ-uint4-svd-r32 [497b2d3cc1] refiner: none vae: none te: none unet: none
Backend: ipex Pipeline: native Cross-attention: Scaled-Dot-Product

Config

{
  "sd_model_checkpoint": "Diffusers/Disty0/FLUX.2-dev-SDNQ-uint4-svd-r32 [497b2d3cc1]",
  "diffusers_version": "c8656ed73c638e51fc2e777a5fd355d69fa5220f",
  "sd_checkpoint_hash": null,
  "diffusers_to_gpu": true,
  "device_map": "gpu",
  "diffusers_offload_mode": "none",
  "ui_request_timeout": 300000,
  "huggingface_token": "hf_...FraU",
  "extra_network_reference_values": true,
  "queue_paused": true
}

Model info

Diffusers/Disty0/FLUX.2-dev-SDNQ-uint4-svd-r32 [497b2d3cc1]

Parameters count is wrong for quantized models

Module	Class	Device	Dtype	Quant	Params	Modules	Config
vae	AutoencoderKLFlux2	xpu:0	torch.bfloat16	None	84046115	244	FrozenDict({'in_channels': 3, 'out_channels': 3, 'down_block_types': ['DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D'], 'up_block_types': ['UpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D'], 'block_out_channels': [128, 256, 512, 512], 'layers_per_block': 2, 'act_fn': 'silu', 'latent_channels': 32, 'norm_num_groups': 32, 'sample_size': 1024, 'force_upcast': True, 'use_quant_conv': True, 'use_post_quant_conv': True, 'mid_block_add_attention': True, 'batch_norm_eps': 0.0001, 'batch_norm_momentum': 0.1, 'patch_size': [2, 2], '_class_name': 'AutoencoderKLFlux2', '_diffusers_version': '0.36.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--Disty0--FLUX.2-dev-SDNQ-uint4-svd-r32/snapshots/497b2d3cc195d985f98f713a38c16e165a808c8b/vae'})
text_encoder	Mistral3ForConditionalGeneration	cpu	torch.bfloat16	QuantizationMethod.SDNQ	13251660800	853	Mistral3Config { "architectures": [ "Mistral3ForConditionalGeneration" ], "dtype": "bfloat16", "image_token_index": 10, "model_type": "mistral3", "multimodal_projector_bias": false, "projector_hidden_act": "gelu", "quantization_config": { "add_skip_keys": false, "dequantize_fp32": false, "group_size": 0, "is_integer": true, "is_training": false, "modules_dtype_dict": {}, "modules_to_not_convert": [ ".img_out", "wte", "patch_emb", ".final_layer", "multi_modal_projector", "time_text_embed", ".emb_in", ".img_in", ".condition_embedder", "lm_head.weight", "lm_head", ".emb_out", "patch_embed", ".txt_in", ".time_embed", ".context_embedder", ".x_embedder", ".vid_in", ".txt_out", ".norm_out", ".vid_out", ".proj_out", "patch_embedding" ], "non_blocking": false, "quant_conv": false, "quant_method": "sdnq", "quantization_device": null, "quantized_matmul_dtype": null, "return_device": null, "svd_rank": 32, "svd_steps": 8, "use_grad_ckpt": true, "use_quantized_matmul": false, "use_quantized_matmul_conv": false, "use_static_quantization": true, "use_stochastic_rounding": false, "use_svd": true, "weights_dtype": "uint4" }, "spatial_merge_size": 2, "text_config": { "attention_dropout": 0.0, "dtype": "bfloat16", "head_dim": 128, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 32768, "max_position_embeddings": 131072, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000000.0, "sliding_window": null, "use_cache": true, "vocab_size": 131072 }, "transformers_version": "4.57.1", "vision_config": { "attention_dropout": 0.0, "dtype": "bfloat16", "head_dim": 64, "hidden_act": "silu", "hidden_size": 1024, "image_size": 1540, "initializer_range": 0.02, "intermediate_size": 4096, "model_type": "pixtral", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 24, "patch_size": 14, "rope_theta": 10000.0 }, "vision_feature_layer": -1 }
tokenizer	PixtralProcessor	None	None	None	0	0	None
scheduler	FlowMatchEulerDiscreteScheduler	None	None	None	0	0	FrozenDict({'num_train_timesteps': 1000, 'shift': 3.0, 'use_dynamic_shifting': True, 'base_shift': 0.5, 'max_shift': 1.15, 'base_image_seq_len': 256, 'max_image_seq_len': 4096, 'invert_sigmas': False, 'shift_terminal': None, 'use_karras_sigmas': False, 'use_exponential_sigmas': False, 'use_beta_sigmas': False, 'time_shift_type': 'exponential', 'stochastic_sampling': False, '_class_name': 'FlowMatchEulerDiscreteScheduler', '_diffusers_version': '0.36.0.dev0'})
transformer	Flux2Transformer2DModel	xpu:0	torch.bfloat16	QuantizationMethod.SDNQ	17211867136	702	FrozenDict({'patch_size': 1, 'in_channels': 128, 'out_channels': None, 'num_layers': 8, 'num_single_layers': 48, 'attention_head_dim': 128, 'num_attention_heads': 48, 'joint_attention_dim': 15360, 'timestep_guidance_channels': 256, 'mlp_ratio': 3.0, 'axes_dims_rope': [32, 32, 32, 32], 'rope_theta': 2000, 'eps': 1e-06, '_class_name': 'Flux2Transformer2DModel', '_diffusers_version': '0.36.0.dev0', '_name_or_path': 'Disty0/FLUX.2-dev-SDNQ-uint4-svd-r32', 'quantization_config': {'weights_dtype': 'uint4', 'quantized_matmul_dtype': None, 'is_training': False, 'quant_method': , 'group_size': 0, 'svd_rank': 32, 'svd_steps': 8, 'use_svd': True, 'use_grad_ckpt': True, 'quant_conv': False, 'use_quantized_matmul': False, 'use_quantized_matmul_conv': False, 'use_static_quantization': True, 'use_stochastic_rounding': False, 'dequantize_fp32': False, 'non_blocking': False, 'add_skip_keys': False, 'quantization_device': None, 'return_device': None, 'modules_to_not_convert': ['x_embedder', 'context_embedder', 'double_stream_modulation_img', 'single_stream_modulation', 'double_stream_modulation_txt', 'norm_out', 'time_guidance_embed', '.proj_out'], 'modules_dtype_dict': {}, 'is_integer': True}, '_pre_quantization_dtype': torch.bfloat16})