Mirror published Civitai release: Fun Photography Sliders — Fisheye
Browse files
photography-sliders/fisheye/Fun_Lens_Sliders_Single_Pass.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b6bf4e2bcb8788c4f36bdb61cf777e9f6e49a5ec280d9f2089d0179f4bd4611
|
| 3 |
+
size 4522
|
photography-sliders/fisheye/README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Fun Photography Sliders — Fisheye
|
| 2 |
+
|
| 3 |
+
Published by **Coffmeteor** for **Krea 2**.
|
| 4 |
+
|
| 5 |
+
[Original Civitai release](https://civitai.red/models/2953827?modelVersionId=3394371) · Version: Fisheye v1.0
|
| 6 |
+
|
| 7 |
+
The files below preserve the exact published Civitai bytes. SHA-256 checksums are included.
|
| 8 |
+
|
| 9 |
+
## Downloads
|
| 10 |
+
|
| 11 |
+
| File | Type |
|
| 12 |
+
|---|---|
|
| 13 |
+
| [Fun_Lens_Sliders_Single_Pass.zip](Fun_Lens_Sliders_Single_Pass.zip) | Workflow |
|
| 14 |
+
| [fisheye.safetensors](fisheye.safetensors) | Model |
|
| 15 |
+
|
| 16 |
+
## Usage
|
| 17 |
+
|
| 18 |
+
The Civitai trigger field is empty; follow the published usage notes below.
|
| 19 |
+
|
| 20 |
+
Verified default adapter strength: 3.5.
|
| 21 |
+
|
| 22 |
+
Fisheye adds wide-angle barrel distortion: curved walls, windows, shelves and horizons, with expanded foreground perspective and sometimes rounded black corners.
|
| 23 |
+
|
| 24 |
+
For Krea 2. Start at strength 3.5; 0 is off. No trigger words are required. Use an ordinary scene description and a model-only LoRA loader (or set CLIP strength to 0).
|
| 25 |
+
|
| 26 |
+
Tested settings: official Krea 2 Turbo BF16, 768 × 1344, 8 total steps, CFG 1, Euler ancestral / beta. Text encoder: qwen3vl_4b_fp8_scaled.safetensors. VAE: qwen/qwen_image_vae.safetensors. Examples use no face restoration or detailer.
|
| 27 |
+
|
| 28 |
+
Recommended strength: 3–3.5. Use ordinary single-pass 8-step sampling with the LoRA active throughout. Adjust model strength directly. Set Honeycomb Prism to 0 when using Fisheye alone.
|
| 29 |
+
|
| 30 |
+
Six different portrait examples at 3.5 show clear curved geometry. Framing, pose, faces and small props can also change. This is a generative lens effect.
|
| 31 |
+
|
| 32 |
+
### Published model notes
|
| 33 |
+
|
| 34 |
+
Six adjustable LoRA sliders for playful, imperfect photography. Each version controls one effect:
|
| 35 |
+
|
| 36 |
+
• Yellow-Green Color Cast — a warm yellow-green tint.
|
| 37 |
+
|
| 38 |
+
• Direct Flash — a direct, on-camera flash look.
|
| 39 |
+
|
| 40 |
+
• Defocus — missed-focus softness and diffuse edges.
|
| 41 |
+
|
| 42 |
+
• Motion Trails — motion blur and trailing softness.
|
| 43 |
+
|
| 44 |
+
• Fisheye — curved wide-angle geometry.
|
| 45 |
+
|
| 46 |
+
• Honeycomb Prism — repeated views inside refractive polygonal cells.
|
| 47 |
+
|
| 48 |
+
For Krea 2. No trigger words required. Load like a normal LoRA and adjust model strength; 0 is off. In ComfyUI, use Load LoRA (model only), or a regular LoRA loader with CLIP strength 0. Use one effect or combine several.
|
| 49 |
+
|
| 50 |
+
Start with Color Cast 2, Direct Flash 2, Defocus 5, or Motion Trails 3. Available slider ranges: 0–3 / 0–3 / 0–10 / 0–6. Strong portrait examples use Defocus 10 or Motion Trails 4.5–6. These are scene-dependent: higher weights can also change facial details, clothing, pose and composition.
|
| 51 |
+
|
| 52 |
+
Includes a ComfyUI workflow with draggable sliders and 4-, 6-, or 9-photo collages. Each photo has its own prompt, seed and four controls: use no effects, one effect, or stack several. Requires Goohaitools-ComfyUI and ComfyUI-Easy-Use. All three collage sizes were tested.
|
| 53 |
+
|
| 54 |
+
Tested with Krea 2 Turbo BF16, 8 steps, CFG 1, Euler ancestral / beta. Each version has a young adult portrait strength comparison using the same prompt and seed. No effect words or post-processing blur were added to the comparisons.
|
| 55 |
+
|
| 56 |
+
Standalone collage workflow: Download the 4/6/9-photo workflow JSON and ZIP (https://civitai.red/models/2953917). See the nine-photo result and workflow-controls screenshot (https://civitai.red/posts/31154443).
|
| 57 |
+
|
| 58 |
+
New lens effects: Fisheye — curved wide-angle geometry, recommended 3–3.5, start 3.5. Honeycomb Prism — repeated photographic views inside glass-edged polygonal cells, recommended 3–4, start 3.5. Both use ordinary single-pass 8-step sampling with the selected LoRA active throughout. Tested with official Krea 2 Turbo BF16, 768 × 1344, CFG 1, Euler ancestral / beta. Adjust model strength directly; no trigger words or special sampling schedule are needed. Faces, clothing, poses, surface details and framing can change. The single-pass workflow ZIP and metadata PNG examples are included.
|
| 59 |
+
|
| 60 |
+
## Provenance and terms
|
| 61 |
+
|
| 62 |
+
The original public descriptions, exact trigger field, permission flags and file metadata are retained in [source.json](source.json). Original model and component terms remain applicable; this mirror does not grant a different license.
|
| 63 |
+
|
| 64 |
+
[SHA-256 checksums](SHA256SUMS)
|
photography-sliders/fisheye/SHA256SUMS
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
5b6bf4e2bcb8788c4f36bdb61cf777e9f6e49a5ec280d9f2089d0179f4bd4611 Fun_Lens_Sliders_Single_Pass.zip
|
| 2 |
+
0b1f500524349ff357ccf21aa8cc5aac4320c337f7a9ffad9486ef3dec00ea1e fisheye.safetensors
|
photography-sliders/fisheye/fisheye.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b1f500524349ff357ccf21aa8cc5aac4320c337f7a9ffad9486ef3dec00ea1e
|
| 3 |
+
size 114324008
|
photography-sliders/fisheye/source.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_id": 2953827,
|
| 3 |
+
"version_id": 3394371,
|
| 4 |
+
"title": "Fun Photography Sliders — Fisheye",
|
| 5 |
+
"source_model_name": "Fun Photography Sliders",
|
| 6 |
+
"source_version_name": "Fisheye v1.0",
|
| 7 |
+
"base_model": "Krea 2",
|
| 8 |
+
"type": "LORA",
|
| 9 |
+
"source_url": "https://civitai.red/models/2953827?modelVersionId=3394371",
|
| 10 |
+
"trained_words": [],
|
| 11 |
+
"verified_usage": [
|
| 12 |
+
{
|
| 13 |
+
"trigger": "",
|
| 14 |
+
"default_strength": 3.5
|
| 15 |
+
}
|
| 16 |
+
],
|
| 17 |
+
"source_model_description_html": "<p>Six adjustable LoRA sliders for playful, imperfect photography. Each version controls one effect:</p><p>• Yellow-Green Color Cast — a warm yellow-green tint.</p><p>• Direct Flash — a direct, on-camera flash look.</p><p>• Defocus — missed-focus softness and diffuse edges.</p><p>• Motion Trails — motion blur and trailing softness.</p><p>• Fisheye — curved wide-angle geometry.</p><p>• Honeycomb Prism — repeated views inside refractive polygonal cells.</p><p>For Krea 2. No trigger words required. Load like a normal LoRA and adjust model strength; 0 is off. In ComfyUI, use Load LoRA (model only), or a regular LoRA loader with CLIP strength 0. Use one effect or combine several.</p><p>Start with Color Cast 2, Direct Flash 2, Defocus 5, or Motion Trails 3. Available slider ranges: 0–3 / 0–3 / 0–10 / 0–6. Strong portrait examples use Defocus 10 or Motion Trails 4.5–6. These are scene-dependent: higher weights can also change facial details, clothing, pose and composition.</p><p>Includes a ComfyUI workflow with draggable sliders and 4-, 6-, or 9-photo collages. Each photo has its own prompt, seed and four controls: use no effects, one effect, or stack several. Requires Goohaitools-ComfyUI and ComfyUI-Easy-Use. All three collage sizes were tested.</p><p>Tested with Krea 2 Turbo BF16, 8 steps, CFG 1, Euler ancestral / beta. Each version has a young adult portrait strength comparison using the same prompt and seed. No effect words or post-processing blur were added to the comparisons.</p><p><strong>Standalone collage workflow:</strong> <a rel=\"ugc\" href=\"https://civitai.red/models/2953917\">Download the 4/6/9-photo workflow JSON and ZIP</a>. See the <a rel=\"ugc\" href=\"https://civitai.red/posts/31154443\">nine-photo result and workflow-controls screenshot</a>.</p><p><strong>New lens effects:</strong> Fisheye — curved wide-angle geometry, recommended 3–3.5, start 3.5. Honeycomb Prism — repeated photographic views inside glass-edged polygonal cells, recommended 3–4, start 3.5. Both use ordinary single-pass 8-step sampling with the selected LoRA active throughout. Tested with official Krea 2 Turbo BF16, 768 × 1344, CFG 1, Euler ancestral / beta. Adjust model strength directly; no trigger words or special sampling schedule are needed. Faces, clothing, poses, surface details and framing can change. The single-pass workflow ZIP and metadata PNG examples are included.</p>",
|
| 18 |
+
"source_version_description_html": "<p><strong>Fisheye</strong> adds wide-angle barrel distortion: curved walls, windows, shelves and horizons, with expanded foreground perspective and sometimes rounded black corners.</p><p>For Krea 2. Start at strength <strong>3.5</strong>; 0 is off. No trigger words are required. Use an ordinary scene description and a model-only LoRA loader (or set CLIP strength to 0).</p><p>Tested settings: official Krea 2 Turbo BF16, 768 × 1344, 8 total steps, CFG 1, Euler ancestral / beta. Text encoder: qwen3vl_4b_fp8_scaled.safetensors. VAE: qwen/qwen_image_vae.safetensors. Examples use no face restoration or detailer.</p><p>Recommended strength: <strong>3–3.5</strong>. Use ordinary single-pass 8-step sampling with the LoRA active throughout. Adjust model strength directly. Set Honeycomb Prism to 0 when using Fisheye alone.</p><p>Six different portrait examples at 3.5 show clear curved geometry. Framing, pose, faces and small props can also change. This is a generative lens effect.</p>",
|
| 19 |
+
"permissions": {
|
| 20 |
+
"allowNoCredit": true,
|
| 21 |
+
"allowCommercialUse": [
|
| 22 |
+
"Image",
|
| 23 |
+
"RentCivit",
|
| 24 |
+
"Rent",
|
| 25 |
+
"Sell",
|
| 26 |
+
"SellMerge"
|
| 27 |
+
],
|
| 28 |
+
"allowDerivatives": true,
|
| 29 |
+
"allowDifferentLicense": true
|
| 30 |
+
},
|
| 31 |
+
"files": [
|
| 32 |
+
{
|
| 33 |
+
"id": 3284489,
|
| 34 |
+
"name": "Fun_Lens_Sliders_Single_Pass.zip",
|
| 35 |
+
"type": "Workflow",
|
| 36 |
+
"path": "photography-sliders/fisheye/Fun_Lens_Sliders_Single_Pass.zip",
|
| 37 |
+
"sha256": "5b6bf4e2bcb8788c4f36bdb61cf777e9f6e49a5ec280d9f2089d0179f4bd4611",
|
| 38 |
+
"size_kb": 4.416015625,
|
| 39 |
+
"metadata": {
|
| 40 |
+
"format": "Other"
|
| 41 |
+
},
|
| 42 |
+
"download_url": "https://civitai.red/api/download/models/3394371?fileId=3284489"
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"id": 3284109,
|
| 46 |
+
"name": "fisheye.safetensors",
|
| 47 |
+
"type": "Model",
|
| 48 |
+
"path": "photography-sliders/fisheye/fisheye.safetensors",
|
| 49 |
+
"sha256": "0b1f500524349ff357ccf21aa8cc5aac4320c337f7a9ffad9486ef3dec00ea1e",
|
| 50 |
+
"size_kb": 111644.5390625,
|
| 51 |
+
"metadata": {
|
| 52 |
+
"format": "SafeTensor",
|
| 53 |
+
"size": "full",
|
| 54 |
+
"fp": "fp32"
|
| 55 |
+
},
|
| 56 |
+
"download_url": "https://civitai.red/api/download/models/3394371?fileId=3284109"
|
| 57 |
+
}
|
| 58 |
+
]
|
| 59 |
+
}
|