Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Info

Image AddedImage Modified

https://huggingface.co/CalamitousFelicitousness/hyphoria_qwen_v1.0-BF16-Diffusers

https://civitai.com/models/2120166/hyphoria-qwen

classsizesfwabstractrealismarttextanimeglass/mirrorcomplex
qwen20Bno one under eighteen starstarstar starstarstarstarstarstar  starstarstarcross mark starstarstarstarstarstar


Code Block
Base Generation
Sampler: res_3s
Scheduler: bong_tangent
Steps: varies (8-12)
CFG: always 1
Lightning 8-step strength: 0.5-0.55

Hires (Latent Upscale)

Sampler: res_2s
Scheduler: bong_tangent
Steps: varies (6-12)
CFG: always 1
Lightning 8-step strength: 0.4-0.5

Related

Test 40 - Qwen Image

Test 46 - Qwen Image Pruning 13B

Test 1 - 1 - Quick Check Samplers

Reference image is https://civitai.com/images/114935442 by ecaj

...

Test 2 - Different resolution

2.1 Square

Steps: 12| Sampler: Euler FlowMatch| Seed: 790287152772005|  CFG true: 4

512x512656x656768x7681024x10241328x13281536x15362048x2048

Image Added

Image Added

Image Added

Image Added

Image Added

Image Added


2.2 Vertical

1136x1472928x1664

Image Added

Image Added


2.3 Horisontal

1472x11361664x928

Image Added

Image Added

Test 3 - Different seed variations

...

AG4, STEP50Seed: 1620085323Seed:1931701040Seed:4075624134Seed:2736029172
bookshop girl

Image Added

Image Added

Image Added

Image Added

hand and face

Image Added

Image Added

Image Added

Image Added

hand and face

legs and shoes

Image Added

Image Added

Image Added

Image Added


Test 4 - Bookshop

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


203250CFG6CFG7

481632
CFG1

Image Added

Image Added

Image Added

CFG1

Image Added

CFG2

Image Added

Image Added

Image Added

Image Added

CFG3

Image Added

Image Added

Image Added

Image Added

CFG4CFG5

Image Added

Image Added

Image Added

CFG8

Image Added

CFG5

Image Added

Image Added

Image Added

Image Added

CFG6

Image Added

Image Added

Image Added

Image Added

CFG7

Image Added

Image Added

Image Added

Image Added

CFG8

Image Added

Image Added

Image Added

Image Added

AG10

Image Added

Image Added

Image Added

Image Added


Test 5 Test 5 - 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.

Parameters: Steps: 16| Size: 1024x1024| Seed: 4075624134| CFG scale: 5| App: SD.Next| Version: d7eb90e| Pipeline: OvisImagePipeline| Operations: txt2img| Model: Ovis-Image-7B

285H Time: 2m 58.98s | total 180.04 pipeline 177.45 decode 1.51 callback 0.78 gc 0.28 | GPU 21078 MB 17% | RAM 31.23 GB 25%

...




810

14

24
AG1

Image Added

Image Added

Image Added

Image Added

AG2

Image Added

Image Added

Image Added

Image Added

AG3

Image Added

Image Added

Image Added

Image Added

AG4

Image Added

Image Added

Image Added

Image Added

AG5

Image Added

Image Added

Image Added

Image Added

AG6

Image Added

Image Added

Image Added

Image Added

AG8

Image Added

Image Added

Image Added

Image Added

Test 6 - Legs

Prompt: Generate a photo of

Test 6 - 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.

Parameters: Steps: 32| Size: 1024x1024| Seed: 1931701040| CFG scale: 5| App: SD.Next| Version: d7eb90e| Pipeline: OvisImagePipeline| Operations: txt2img| Model: Ovis-Image-7B

285H Time: 5m 56.50s | total 358.27 pipeline 354.97 decode 1.52 callback 1.48 gc 0.29 | GPU 21078 MB 17% | RAM 31.29 GB 25%

...

Test 7 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"

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

Test 8 - 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

...

 

seed 68



8163264
AG1

Image Added

Image Added

Image Added

Image Added

AG2

Image Added

Image Added

Image Added

Image Added

AG3

Image Added

Image Added

Image Added

Image Added

AG4

Image Added

Image Added

Image Added

Image Added

AG5

Image Added

Image Added

Image Added

Image Added

AG6

Image Added

Image Added

Image Added

Image Added

AG8

Image Added

Image Added

Image Added

Image Added

Test 7 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"

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


Test 8 - Empty prompts


1328x1328, Steps 50

Image Added

seed 1

Image Added

seed 2

Image Added

seed 3

Image Added

seed 4

Image Added

seed 5

Image Added

seed 6

Image Added

seed 7

Image Added

seed 8

Image Added

seed 9

Image Added

seed 10

Image Added

seed 21

Image Added

seed 38

Image Added

seed 42

 Image Added

seed 68

Image Added

seed 2025

Test 9 - Other Models cover

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added

Test 10 - Art Prompts

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added\Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added

Test 11 - Search for cover

Image Added

Prompt: Brick wall with bright "Hyphoria Qwen" graffiti .Fantasy wizard girl gently blows a stream of glowing spores and luminous particles from her lips behind the text. Graffiti main colors are Lime and Mint. Dark grey asphalt on a sidewalk below. Large building number sign with text "20B" upper left side the graffiti.

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added




System info

Code Block
Tue Jan  6 20:50:32 2026
app: sdnext.git updated: 2026-01-06 hash: e33daab6a url: https://github.com/liutyi/sdnext/tree/pytorch
arch: x86_64 cpu: x86_64 system: Linux release: 6.17.0-8-generic
python: 3.12.3 Torch: 2.9.1+xpu
device: Intel(R) Arc(TM) Graphics (1) ipex: 
ram: free:119.41 used:3.66 total:123.07
xformers: diffusers: 0.37.0.dev0 transformers: 4.57.3
active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16
base: Diffusers/CalamitousFelicitousness/hyphoria_qwen_v1.0-BF16-Diffusers [bc0f90041c] refiner: none vae: none te: none unet: none
ipex native none Scaled-Dot-Product


Config

Code Block
{
  "diffusers_version": "88ffb0013972c7b9fd3725bcd63e3c3c1400834f",
  "sd_model_checkpoint": "Diffusers/CalamitousFelicitousness/hyphoria_qwen_v1.0-BF16-Diffusers [bc0f90041c]",
  "sd_checkpoint_hash": null,
  "diffusers_offload_mode": "none",
  "huggingface_token": "hf_..raU"
}


Model info

Diffusers/CalamitousFelicitousness/hyphoria_qwen_v1.0-BF16-Diffusers [bc0f90041c]

seed 2025

Test 9 - Other Models cover

Test 10 - Art Prompts

Compare Art to Z Image turbo

System info

Code Block
.

Config

Code Block
{
.
}

...

ModuleClassDeviceDtypeQuantParamsModulesConfig
vaeAutoencoderKLQwenImagexpu:0torch.bfloat16None126892531260

FrozenDict({'base_dim': 96, 'z_dim': 16, 'dim_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_scales': [], 'temperal_downsample': [False, True, True], 'dropout': 0.0, 'input_channels': 3, 'latents_mean': [-0.7571, -0.7089, -0.9113, 0.1075, -0.1745, 0.9653, -0.1517, 1.5508, 0.4134, -0.0715, 0.5517, -0.3632, -0.1922, -0.9497, 0.2503, -0.2921], 'latents_std': [2.8184, 1.4541, 2.3275, 2.6558, 1.2196, 1.7708, 2.6052, 2.0743, 3.2687, 2.1526, 2.8652, 1.5579, 1.6382, 1.1253, 2.8251, 1.916], '_use_default_values': ['input_channels'], '_class_name': 'AutoencoderKLQwenImage', '_diffusers_version': '0.34.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--CalamitousFelicitousness--hyphoria_qwen_v1.0-BF16-Diffusers/snapshots/bc0f90041c79c3cbd1936143e574035335e0207b/vae'})

text_encoderQwen2_5_VLForConditionalGenerationxpu:0torch.bfloat16None8292166656763

Qwen2_5_VLConfig { "architectures": [ "Qwen2_5_VLForConditionalGeneration" ], "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 128000, "max_window_layers": 28, "model_type": "qwen2_5_vl", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sliding_window": 32768, "text_config": { "_name_or_path": "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", "architectures": [ "Qwen2_5_VLForConditionalGeneration" ], "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "image_token_id": 151655, "initializer_range": 0.02, "intermediate_size": 18944, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 128000, "max_window_layers": 28, "model_type": "qwen2_5_vl_text", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sliding_window": null, "use_cache": true, "use_sliding_window": false, "video_token_id": 151656, "vision_end_token_id": 151653, "vision_start_token_id": 151652, "vision_token_id": 151654, "vocab_size": 152064 }, "tie_word_embeddings": false, "transformers_version": "4.57.3", "use_cache": true, "use_sliding_window": false, "vision_config": { "depth": 32, "dtype": "bfloat16", "fullatt_block_indexes": [ 7, 15, 23, 31 ], "hidden_act": "silu", "hidden_size": 1280, "in_channels": 3, "in_chans": 3, "initializer_range": 0.02, "intermediate_size": 3420, "model_type": "qwen2_5_vl", "num_heads": 16, "out_hidden_size": 3584, "patch_size": 14, "spatial_merge_size": 2, "spatial_patch_size": 14, "temporal_patch_size": 2, "tokens_per_second": 2, "window_size": 112 }, "vision_token_id": 151654, "vocab_size": 152064 }

tokenizerQwen2TokenizerNoneNoneNone00

None

transformerQwenImageTransformer2DModelxpu:0torch.bfloat16None204304010882297

FrozenDict({'patch_size': 2, 'in_channels': 64, 'out_channels': 16, 'num_layers': 60, 'attention_head_dim': 128, 'num_attention_heads': 24, 'joint_attention_dim': 3584, 'guidance_embeds': False, 'axes_dims_rope': [16, 56, 56], 'zero_cond_t': False, 'use_additional_t_cond': False, 'use_layer3d_rope': False, '_use_default_values': ['zero_cond_t', 'use_layer3d_rope', 'use_additional_t_cond'], '_class_name': 'QwenImageTransformer2DModel', '_diffusers_version': '0.35.2', 'pooled_projection_dim': 768, '_name_or_path': 'CalamitousFelicitousness/hyphoria_qwen_v1.0-BF16-Diffusers'})

schedulerFlowMatchDPMSolverMultistepSchedulerNoneNoneNone00

FrozenDict({'num_train_timesteps': 1000, 'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'linear', 'trained_betas': None, 'solver_order': 2, 'algorithm_type': 'dpmsolver2', 'solver_type': 'midpoint', 'sigma_schedule': None, 'shift': 3, 'midpoint_ratio': 0.5, 's_noise': 1.0, 'use_noise_sampler': True, 'use_beta_sigmas': False, 'use_dynamic_shifting': False, 'base_shift': 0.5, 'max_shift': 1.15, 'base_image_seq_len': 256, 'max_image_seq_len': 4096, '_use_default_values': ['solver_type', 's_noise', 'midpoint_ratio', 'trained_betas', 'max_image_seq_len', 'base_image_seq_len']})

...