Coffmeteor commited on
Commit
6ee9545
·
verified ·
1 Parent(s): 61dc281

Mirror published Civitai release: Storyflow Three-Frame In-Context

Browse files
storyflow/three-frame-in-context/README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Storyflow Three-Frame In-Context
2
+
3
+ Published by **Coffmeteor** for **Krea 2**.
4
+
5
+ [Original Civitai release](https://civitai.red/models/2891699?modelVersionId=3269328) · Version: v0.1
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
+ | [krea2-meridian-storyboard-v003-final.safetensors](krea2-meridian-storyboard-v003-final.safetensors) | Model |
14
+
15
+ ## Usage
16
+
17
+ The Civitai trigger field is empty; follow the published usage notes below.
18
+
19
+ ### Published model notes
20
+
21
+ Base: Krea2 Turbo BF16
22
+
23
+ Resolution: 512×1536
24
+
25
+ Steps: 8
26
+
27
+ CFG: 1.0
28
+
29
+ Sampler: Euler Ancestral
30
+
31
+ Scheduler: Beta
32
+
33
+ ## Provenance and terms
34
+
35
+ 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.
36
+
37
+ [SHA-256 checksums](SHA256SUMS)
storyflow/three-frame-in-context/SHA256SUMS ADDED
@@ -0,0 +1 @@
 
 
1
+ 0c0a6666ea4f5f95c1be13419e146f3a07addac9f1f74d6c3b29f2772f6f744f krea2-meridian-storyboard-v003-final.safetensors
storyflow/three-frame-in-context/krea2-meridian-storyboard-v003-final.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0a6666ea4f5f95c1be13419e146f3a07addac9f1f74d6c3b29f2772f6f744f
3
+ size 114353200
storyflow/three-frame-in-context/source.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": 2891699,
3
+ "version_id": 3269328,
4
+ "title": "Storyflow Three-Frame In-Context",
5
+ "source_model_name": "Krea2 StoryFlow — 3-Frame In-Context LoRA",
6
+ "source_version_name": "v0.1",
7
+ "base_model": "Krea 2",
8
+ "type": "LORA",
9
+ "source_url": "https://civitai.red/models/2891699?modelVersionId=3269328",
10
+ "trained_words": [],
11
+ "verified_usage": [],
12
+ "source_model_description_html": "<h2>原理</h2><p>参考FLUX In-Context LoRA训练方案训练的Krea2 三帧故事板,仍属于实验中 。</p><p>把三个连续状态放在同一张纵向画布中联合生成,让模型利用画布内上下文保持人物、服装、场景和道具连续,同时表现动作、位置或镜头变化。</p><h2>使用方法</h2><h3>推荐参数:</h3><pre><code>Base: Krea2 Turbo BF16\n\nLoRA strength: 0.85(可尝试 0.7–1.0)\n\nResolution: 512×1536\n\nSteps: 8\n\nCFG: 1.0\n\nSampler: Euler Ancestral\n\nScheduler: Beta</code></pre><h3>提示词格式:</h3><pre><code>[SHOT-SEQUENCE] 三帧共同保持的人物、服装、场景、道具和光线。\n\n[FRAME-1] 初始状态。\n\n[FRAME-2] 中间状态。\n\n[FRAME-3] 最终状态。</code></pre><p>建议先在 <code>512×1536</code> 生成(训练分辨率),再把三格分别超分。不建议直接生成超高纵向分辨率。</p><h3>当前问题</h3><ul><li><p>小幅凝视、表情和手势变化有时不明显。</p></li><li><p>复杂手部与道具交互可能出错或重复道具。</p></li><li><p>强度过高时动作会变保守,后两格可能过于相似。</p></li><li><p>远景人物的脸部细节有限。</p></li></ul><p></p>",
13
+ "source_version_description_html": null,
14
+ "permissions": {
15
+ "allowNoCredit": true,
16
+ "allowCommercialUse": [
17
+ "Image",
18
+ "RentCivit",
19
+ "Rent",
20
+ "Sell",
21
+ "SellMerge"
22
+ ],
23
+ "allowDerivatives": true,
24
+ "allowDifferentLicense": true
25
+ },
26
+ "files": [
27
+ {
28
+ "id": 3153106,
29
+ "name": "krea2-meridian-storyboard-v003-final.safetensors",
30
+ "type": "Model",
31
+ "path": "storyflow/three-frame-in-context/krea2-meridian-storyboard-v003-final.safetensors",
32
+ "sha256": "0c0a6666ea4f5f95c1be13419e146f3a07addac9f1f74d6c3b29f2772f6f744f",
33
+ "size_kb": 111673.046875,
34
+ "metadata": {
35
+ "format": "SafeTensor",
36
+ "fp": "bf16",
37
+ "isRequired": false
38
+ },
39
+ "download_url": "https://civitai.red/api/download/models/3269328?fileId=3153106"
40
+ }
41
+ ]
42
+ }